In [3]:
import cv2
import numpy as np
import matplotlib.pyplot as plt
import matplotlib.image as mpimg
%matplotlib inline
from moviepy.editor import VideoFileClip
In [4]:
# Used the Calibration image from the repository

img = mpimg.imread('camera_cal/calibration2.jpg')
org_img = img
plt.imshow(img)
Out[4]:
<matplotlib.image.AxesImage at 0x1155e8c50>
In [5]:
# Initialized the objpts and imgpts for the chess board example

objpts = []
imgpts = []
objp = np.zeros((6*9, 3), np.float32)
objp[:,:2] = np.mgrid[0:9, 0:6].T.reshape(-1, 2)
In [6]:
# Conversion of BGR to Gray scale image, and used CV2 function to identify corners

gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
ret, corners = cv2.findChessboardCorners(gray, (9,6),None)
print (ret)
True
In [7]:
# Used the CV2 drawChessboardCorners to plot the corners

if ret == True:
    imgpts.append(corners)
    objpts.append(objp)
    
    img - cv2.drawChessboardCorners(img, (8,6), corners, ret)
    plt.imshow(img)
In [8]:
# Used the CV2 calibrateCamera to calibrate using the Chessboard image with the corners

ret, mtx, dist, rvecs, tvecs = cv2.calibrateCamera(objpts, imgpts, gray.shape[::-1], None, None)
In [9]:
# Function to get the undistort image with the give Chess board corner image

undist = cv2.undistort(img, mtx, dist, None, mtx)
plt.imshow(undist)
Out[9]:
<matplotlib.image.AxesImage at 0x1181a97f0>
In [10]:
# Just a show, to display both the original and undistorted image with corners plotted

org_img = mpimg.imread('camera_cal/calibration2.jpg')
f, (ax1, ax2) = plt.subplots(1, 2, figsize=(24, 9))
f.tight_layout()
ax1.imshow(org_img)
ax1.set_title('Original Image', fontsize=50)
ax2.imshow(undist, cmap='gray')
ax2.set_title('Undistorted with Corners', fontsize=50)
plt.subplots_adjust(left=0., right=1, top=0.9, bottom=0.)
In [11]:
# Function to get the Perspective image with the given distorted image

def corners_unwarp_chess(img, nx, ny, mtx, dist):
    # Pass in your image into this function
    # Write code to do the following steps
    # 1) Undistort using mtx and dist
    # 2) Convert to grayscale
    # 3) Find the chessboard corners
    # 4) If corners found: 
            # a) draw corners
            # b) define 4 source points src = np.float32([[,],[,],[,],[,]])
                 #Note: you could pick any four of the detected corners 
                 # as long as those four corners define a rectangle
                 #One especially smart way to do this would be to use four well-chosen
                 # corners that were automatically detected during the undistortion steps
                 #We recommend using the automatic detection of corners in your code
            # c) define 4 destination points dst = np.float32([[,],[,],[,],[,]])
            # d) use cv2.getPerspectiveTransform() to get M, the transform matrix
            # e) use cv2.warpPerspective() to warp your image to a top-down view
    #delete the next two lines

    # Use the OpenCV undistort() function to remove distortion
    undist = cv2.undistort(img, mtx, dist, None, mtx)
    plt.imshow(undist)
    # Convert undistorted image to grayscale
    gray = cv2.cvtColor(undist, cv2.COLOR_BGR2GRAY)
    #plt.imshow(gray)
    # Search for corners in the grayscaled image
    ret, corners = cv2.findChessboardCorners(gray, (nx, ny), None)
    
    print (ret)

    if ret == True:
        # If we found corners, draw them! (just for fun)
        cv2.drawChessboardCorners(undist, (nx, ny), corners, ret)
        # Choose offset from image corners to plot detected corners
        # This should be chosen to present the result at the proper aspect ratio
        # My choice of 100 pixels is not exact, but close enough for our purpose here
        offset = 100 # offset for dst points
        # Grab the image shape
        img_size = (gray.shape[1], gray.shape[0])

        # For source points I'm grabbing the outer four detected corners
        src = np.float32([corners[0], corners[nx-1], corners[-1], corners[-nx]])
        # For destination points, I'm arbitrarily choosing some points to be
        # a nice fit for displaying our warped result 
        # again, not exact, but close enough for our purposes
        dst = np.float32([[offset, offset], [img_size[0]-offset, offset], 
                                     [img_size[0]-offset, img_size[1]-offset], 
                                     [offset, img_size[1]-offset]])
        # Given src and dst points, calculate the perspective transform matrix
        M = cv2.getPerspectiveTransform(src, dst)
        # Warp the image using OpenCV warpPerspective()
        warped = cv2.warpPerspective(undist, M, img_size)

        return warped, M

    return 
In [12]:
img = mpimg.imread('camera_cal/calibration2.jpg')
plt.imshow(img)
Out[12]:
<matplotlib.image.AxesImage at 0x11929d438>
In [13]:
# Used the corners unwarp function to get the perpsective image

nx = 8 # the number of inside corners in x
ny = 6 # the number of inside corners in y
warped2, M = corners_unwarp_chess(img, nx, ny, mtx, dist)
True
In [14]:
# Just a plot to show both the original and undistorted Perspective image

org_img = mpimg.imread('camera_cal/calibration2.jpg')
f, (ax1, ax2) = plt.subplots(1, 2, figsize=(24, 9))
f.tight_layout()
ax1.imshow(org_img)
ax1.set_title('Original Image', fontsize=50)
ax2.imshow(warped2, cmap='gray')
ax2.set_title('Undistorted Perspective Image', fontsize=50)
plt.subplots_adjust(left=0., right=1, top=0.9, bottom=0.)
In [15]:
# This function original image  to undistorted and perspective image

def corners_unwarp(img, mtx, dist):
    
    img_shape = img.shape
    
    print("Image shape:", img_shape)
    
    # Use the OpenCV undistort() function to remove distortion
    undist = cv2.undistort(img, mtx, dist, None, mtx)
    plt.imshow(undist)
    # Convert undistorted image to grayscale
    gray = cv2.cvtColor(undist, cv2.COLOR_BGR2GRAY)
    plt.imshow(gray)
    
    
    # Choose offset from image corners to plot detected corners
    # This should be chosen to present the result at the proper aspect ratio
    # My choice of 100 pixels is not exact, but close enough for our purpose here
    offset = 100 # offset for dst points
    # Grab the image shape
    img_size = (gray.shape[1], gray.shape[0])

    #corners = [[580, 460],[710,460],[1150,720],[150,720]]
    #corners = [[580, 460],[750,460],[1150,720],[150,720]]
    #corners = [[220,720], [1110, 720], [722, 470], [570, 470]]

    #corners_dst = [[320,720], [920, 720], [920, 1], [320, 1]]

    #src = np.array([[580, 460],[750,460],[1150,720],[150,720]]).astype(np.float32)
    #dst = np.array([[320,720], [920, 720], [920, 1], [320, 1]]).astype(np.float32)
    
    #Worksrc = np.array([[585, 460], [203, 720], [1127, 720], [695, 460]]).astype(np.float32)
    #Workdst = np.array([[320, 0], [320, 720], [960, 720], [960, 0]]).astype(np.float32)

    #work 2 src = np.array([[585, 460], [270, 720], [1127, 720], [695, 460]]).astype(np.float32)
    
    src = np.array([[585, 460], [280, 720], [1127, 720], [695, 460]]).astype(np.float32)
    dst = np.array([[320, 0], [320, 720], [960, 720], [960, 0]]).astype(np.float32)
    
    # For source points I'm grabbing the outer four detected corners
    #src = np.float32(corners)
    # For destination points, I'm arbitrarily choosing some points to be
    # a nice fit for displaying our warped result 
    # again, not exact, but close enough for our purposes
    #dst = np.float32([[offset, offset], [img_size[0]-offset, offset], 
                                     #[img_size[0]-offset, img_size[1]-0], 
                                     #[offset, img_size[1]-0]])
    
    #src = np.float32(corners)
    #dst = np.float32(corners_dst)
    # Given src and dst points, calculate the perspective transform matrix
    M = cv2.getPerspectiveTransform(src, dst)
    MInv = cv2.getPerspectiveTransform(dst, src)
    # Warp the image using OpenCV warpPerspective()
    warped = cv2.warpPerspective(undist, M, img_size)

    return warped, M, MInv, undist
In [247]:
# Define a class to receive the characteristics of each line detection
class Line():
    def __init__(self):
        # was the line detected in the last iteration?
        self.detected = False  
        # x, y values of the last n fits of the line
        self.recent_xfitted = collections.deque(maxlen=cache_size)
        self.recent_yfitted = collections.deque(maxlen=cache_length)
        
        #average x values of the fitted line over the last n iterations
        self.bestx = None     
        #polynomial coefficients averaged over the last n iterations
        self.best_fit = None  
        #polynomial coefficients for the most recent fit
        self.current_fit = [np.array([False])]  
        #radius of curvature of the line in some units
        self.radius_of_curvature = None 
        #distance in meters of vehicle center from the line
        self.line_base_pos = None 
        #difference in fit coefficients between last and new fits
        self.diffs = np.array([0,0,0], dtype='float') 
        #x values for detected line pixels
        self.allx = None  
        #y values for detected line pixels
        self.ally = None
        
    def sanity_check(self, curvature):
        
        if self.radius_of_curvature is None:
            return True
        
        self.in_sanity = abs(curvature-self.radius_of_curvature )/self.radius_of_curvature 
        return self.in_sanity <= 0.5 
        
In [16]:
img = mpimg.imread('test_images/test1.jpg')
plt.imshow(img)
Out[16]:
<matplotlib.image.AxesImage at 0x105cf5d30>
In [17]:
# Called the corners_unwarp to get the Perspective image

gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
ret, mtx, dist, rvecs, tvecs = cv2.calibrateCamera(objpts, imgpts, gray.shape[::-1], None, None)

warped2, M, Minv, undist = corners_unwarp(img, mtx, dist)
plt.imshow(warped2)
Image shape: (720, 1280, 3)
Out[17]:
<matplotlib.image.AxesImage at 0x105d08160>
In [18]:
# Just a plot to show the Original Image and Undistorted Image

f, (ax1, ax2) = plt.subplots(1, 2, figsize=(24, 9))
f.tight_layout()
ax1.imshow(img)
ax1.set_title('Original Image', fontsize=50)
ax2.imshow(undist, cmap='gray')
ax2.set_title('Undistorted Image', fontsize=50)
plt.subplots_adjust(left=0., right=1, top=0.9, bottom=0.)
In [19]:
def abs_sobel_thresh(img, orient='x', sobel_kernel=3, thresh=(0, 255)):
    
    # Apply the following steps to img
    # 1) Convert to grayscale
    # 2) Take the derivative in x or y given orient = 'x' or 'y'
    # 3) Take the absolute value of the derivative or gradient
    # 4) Scale to 8-bit (0 - 255) then convert to type = np.uint8
    # 5) Create a mask of 1's where the scaled gradient magnitude 
            # is > thresh_min and < thresh_max
    # 6) Return this mask as your binary_output image
    
    
    gray = cv2.cvtColor(img, cv2.COLOR_RGB2GRAY)
    # Apply x or y gradient with the OpenCV Sobel() function
    # and take the absolute value
    if orient == 'x':
        abs_sobel = np.absolute(cv2.Sobel(gray, cv2.CV_64F, 1, 0, ksize=sobel_kernel))
    if orient == 'y':
        abs_sobel = np.absolute(cv2.Sobel(gray, cv2.CV_64F, 0, 1, ksize=sobel_kernel))
    # Rescale back to 8 bit integer
    scaled_sobel = np.uint8(255*abs_sobel/np.max(abs_sobel))
    # Create a copy and apply the threshold
    binary_output = np.zeros_like(scaled_sobel)
    # Here I'm using inclusive (>=, <=) thresholds, but exclusive is ok too
    binary_output[(scaled_sobel >= thresh[0]) & (scaled_sobel <= thresh[1])] = 1

    return binary_output
In [20]:
def mag_thresh(img, sobel_kernel=3, mag_thresh=(0, 255)):
    
    # Apply the following steps to img
    # 1) Convert to grayscale
    # 2) Take the gradient in x and y separately
    # 3) Calculate the magnitude 
    # 4) Scale to 8-bit (0 - 255) and convert to type = np.uint8
    # 5) Create a binary mask where mag thresholds are met
    # 6) Return this mask as your binary_output image
    
     # Convert to grayscale
    gray = cv2.cvtColor(img, cv2.COLOR_RGB2GRAY)
    # Take both Sobel x and y gradients
    sobelx = cv2.Sobel(gray, cv2.CV_64F, 1, 0, ksize=sobel_kernel)
    sobely = cv2.Sobel(gray, cv2.CV_64F, 0, 1, ksize=sobel_kernel)
    # Calculate the gradient magnitude
    gradmag = np.sqrt(sobelx**2 + sobely**2)
    # Rescale to 8 bit
    scale_factor = np.max(gradmag)/255 
    gradmag = (gradmag/scale_factor).astype(np.uint8) 
    # Create a binary image of ones where threshold is met, zeros otherwise
    binary_output = np.zeros_like(gradmag)
    binary_output[(gradmag >= mag_thresh[0]) & (gradmag <= mag_thresh[1])] = 1


    return binary_output
In [21]:
# Run the function
mag_binary = mag_thresh(img, sobel_kernel=3, mag_thresh=(40, 200))
# Plot the result
f, (ax1, ax2) = plt.subplots(1, 2, figsize=(24, 9))
f.tight_layout()
ax1.imshow(img)
ax1.set_title('Original Image', fontsize=50)
ax2.imshow(mag_binary, cmap='gray')
ax2.set_title('Thresholded Magnitude', fontsize=50)
plt.subplots_adjust(left=0., right=1, top=0.9, bottom=0.)
In [22]:
# Define a function that applies Sobel x and y, 
# then computes the direction of the gradient
# and applies a threshold.

def dir_threshold(img, sobel_kernel=3, thresh=(0, np.pi/2)):
    
    # Apply the following steps to img
    # 1) Convert to grayscale
    # 2) Take the gradient in x and y separately
    # 3) Take the absolute value of the x and y gradients
    # 4) Use np.arctan2(abs_sobely, abs_sobelx) to calculate the direction of the gradient 
    # 5) Create a binary mask where direction thresholds are met
    # 6) Return this mask as your binary_output image
    gray = cv2.cvtColor(img, cv2.COLOR_RGB2GRAY)
    # Calculate the x and y gradients
    sobelx = cv2.Sobel(gray, cv2.CV_64F, 1, 0, ksize=sobel_kernel)
    sobely = cv2.Sobel(gray, cv2.CV_64F, 0, 1, ksize=sobel_kernel)
    # Take the absolute value of the gradient direction, 
    # apply a threshold, and create a binary image result
    absgraddir = np.arctan2(np.absolute(sobely), np.absolute(sobelx))
    binary_output =  np.zeros_like(absgraddir)
    binary_output[(absgraddir >= thresh[0]) & (absgraddir <= thresh[1])] = 1

    return binary_output
In [23]:
# Run the function to get direction threshold

dir_binary = dir_threshold(img, sobel_kernel=15, thresh=(0.7, 1.3))
# Plot the result
f, (ax1, ax2) = plt.subplots(1, 2, figsize=(24, 9))
f.tight_layout()
ax1.imshow(img)
ax1.set_title('Original Image', fontsize=50)
ax2.imshow(dir_binary, cmap='gray')
ax2.set_title('Thresholded Grad. Dir.', fontsize=50)
plt.subplots_adjust(left=0., right=1, top=0.9, bottom=0.)
In [24]:
# Choose a Sobel kernel size

ksize = 3 # Choose a larger odd number to smooth gradient measurements

# Apply each of the thresholding functions
gradx = abs_sobel_thresh(img, orient='x', sobel_kernel=ksize, thresh=(10, 200))
grady = abs_sobel_thresh(img, orient='y', sobel_kernel=ksize, thresh=(10, 200))
mag_binary = mag_thresh(img, sobel_kernel=ksize, mag_thresh=(40, 200))
dir_binary = dir_threshold(img, sobel_kernel=ksize, thresh=(0, np.pi/2))
In [25]:
# Gets the combined image

combined = np.zeros_like(dir_binary)
combined[((gradx == 1) & (grady == 1)) | ((mag_binary == 1) & (dir_binary == 1))] = 1
In [26]:
# Plot to show both the original image, and Combined gradiant image

f, (ax1, ax2) = plt.subplots(1, 2, figsize=(24, 9))
f.tight_layout()
ax1.imshow(img)
ax1.set_title('Original Image', fontsize=50)
ax2.imshow(combined, cmap='gray')
ax2.set_title('Combined Grad. Image', fontsize=50)
plt.subplots_adjust(left=0., right=1, top=0.9, bottom=0.)
In [27]:
# To show the HLS usage with S channel, and plotted both original and combined image with S channel

hls = cv2.cvtColor(img, cv2.COLOR_RGB2HLS)
s = hls[:,:,2]
s_binary = np.zeros_like(combined)
s_binary[(s > 170) & (s < 255)] = 1
color_binary = np.zeros_like(combined)
color_binary[(s_binary > 0) | (combined > 0)] = 1

f, (ax1, ax2) = plt.subplots(1, 2, figsize=(24, 9))
f.tight_layout()
ax1.imshow(img)
ax1.set_title('Original Image', fontsize=50)
ax2.imshow(color_binary, cmap='gray')
ax2.set_title('S channel + Combined Image', fontsize=50)
plt.subplots_adjust(left=0., right=1, top=0.9, bottom=0.)
In [28]:
# Tested the historgram

import numpy as np
histogram = np.sum(color_binary[color_binary.shape[0]//2:,:], axis=0)
plt.plot(histogram)
Out[28]:
[<matplotlib.lines.Line2D at 0x11979b4e0>]
In [29]:
warped2, M, Minv, undist = corners_unwarp(img, mtx, dist)
plt.imshow(warped2)
Image shape: (720, 1280, 3)
Out[29]:
<matplotlib.image.AxesImage at 0x1192ae630>
In [30]:
import numpy as np
histogram = np.sum(warped2[warped2.shape[0]//2:,:], axis=0)
# plt.plot(histogram)
In [31]:
# Main pipline code that does the Undistort, threshold, HLS/S-channel

def pipeline5(img):

    ksize = 3 # Choose a larger odd number to smooth gradient measurements
    #img = cv2.resize(img, (720, 405))
    #img = cv2.GaussianBlur(img, (ksize, ksize), 0)
    gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
    ret, mtx, dist, rvecs, tvecs = cv2.calibrateCamera(objpts, imgpts, gray.shape[::-1], None, None)

    warped, M, Minv, undist = corners_unwarp(img, mtx, dist)
   
    hls = cv2.cvtColor(warped, cv2.COLOR_RGB2HLS)
    
    s = hls[:,:,2]
    h = hls[:,:,0]
    l = hls[:,:,1]
    
        
    #plt.imshow(img)
    ksize = 7
    # Apply each of the thresholding functions
    gradx = abs_sobel_thresh(warped, orient='x', sobel_kernel=ksize, thresh=(40, 255))
    grady = abs_sobel_thresh(warped, orient='y', sobel_kernel=ksize, thresh=(40, 255))
    mag_binary = mag_thresh(warped, sobel_kernel=ksize, mag_thresh=(40, 200))
    #plt.imshow(mag_binary)
    dir_binary = dir_threshold(warped, sobel_kernel=ksize, thresh=(0, np.pi/2))
    
    combined = np.zeros_like(dir_binary)
    combined[((gradx == 1) & (grady == 1)) | ((mag_binary == 1) & (dir_binary == 1))] = 1
    

    s_binary = np.zeros_like(combined)
    h_binary = np.zeros_like(combined)
    #l_binary = np.zeros_like(combined)
    
    s_binary[(s > 200) & (s < 255)] = 1
    #h_binary[(h > 20) & (h < 50)] = 1
    #l_binary[(l > 150) & (l < 255)] = 1
    
    color_binary = np.zeros_like(combined)
    color_binary[(s_binary > 0) | (combined > 0)] = 1
    
    #final_binary = np.zeros_like(color_binary)
    #final_binary[((h_binary > 0) & (l_binary > 0)) | (combined > 0)] = 1
    #final_binary[((h_binary > 0) & (s_binary > 0)) | (combined > 0)] = 1
   
    return warped, M, Minv, color_binary, undist
In [87]:
# Main pipline code that does the Undistort, threshold, HLS/S-channel

def pipeline4(img):

    ksize = 3 # Choose a larger odd number to smooth gradient measurements
    #img = cv2.resize(img, (720, 405))
    #img = cv2.GaussianBlur(img, (ksize, ksize), 0)
    gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
    ret, mtx, dist, rvecs, tvecs = cv2.calibrateCamera(objpts, imgpts, gray.shape[::-1], None, None)

    warped, M, Minv, undist = corners_unwarp(img, mtx, dist)
   
    
    hls = cv2.cvtColor(warped, cv2.COLOR_RGB2HLS)
    
    s = hls[:,:,2]
    h = hls[:,:,0]
    l = hls[:,:,1]
    
        
    #plt.imshow(img)
    ksize = 7
    # Apply each of the thresholding functions
    gradx = abs_sobel_thresh(warped, orient='x', sobel_kernel=ksize, thresh=(10, 250))
    grady = abs_sobel_thresh(warped, orient='y', sobel_kernel=ksize, thresh=(10, 250))
    mag_binary = mag_thresh(warped, sobel_kernel=ksize, mag_thresh=(10, 200))
    #plt.imshow(mag_binary)
    dir_binary = dir_threshold(warped, sobel_kernel=ksize, thresh=(0, np.pi/2))
    
    combined = np.zeros_like(dir_binary)
    combined[((gradx == 1) & (grady == 1)) | ((mag_binary == 1) & (dir_binary == 1))] = 1
    

    s_binary = np.zeros_like(combined)
    h_binary = np.zeros_like(combined)
    l_binary = np.zeros_like(combined)
    
    s_binary[(s > 170) & (s < 255)] = 1
    h_binary[(h > 20) & (h < 50)] = 1
    l_binary[(l > 50) & (l < 255)] = 1
    
    #color_binary = np.zeros_like(combined)
    #color_binary[(s_binary > 0) | (combined > 0)] = 1
    
    
    image_HSV = cv2.cvtColor(warped,cv2.COLOR_RGB2HSV)
    yellow_hsv_low  = np.array([ 0,  100,  100])
    yellow_hsv_high = np.array([ 80, 255, 255])
    white_hsv_low  = np.array([ 0,   0,   160])
    white_hsv_high = np.array([ 255,  80, 255])
    mask_yellow =cv2.inRange(image_HSV, yellow_hsv_low, yellow_hsv_high)
    mask_white = cv2.inRange(image_HSV,white_hsv_low,white_hsv_high)
    mask_lane = cv2.bitwise_or(mask_yellow,mask_white)

    color_binary[(mask_lane > 0) | (combined > 0)] = 1

    return warped, M, Minv, color_binary, undist
In [274]:
def pipeline3(img):

    ksize = 3 # Choose a larger odd number to smooth gradient measurements
    #img = cv2.resize(img, (720, 405))
    #img = cv2.GaussianBlur(img, (ksize, ksize), 0)
    gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
    ret, mtx, dist, rvecs, tvecs = cv2.calibrateCamera(objpts, imgpts, gray.shape[::-1], None, None)

    warped, M, Minv, undist = corners_unwarp(img, mtx, dist)
   
    hls = cv2.cvtColor(warped, cv2.COLOR_RGB2HLS)
    
    s = hls[:,:,2]
    h = hls[:,:,0]
    l = hls[:,:,1]
    
    r = warped[:,:,0] 
    
    #threshold for Rchannel
    r_binary = np.zeros_like(r)
    r_binary[(r >= 100) & (r <= 255)] = 1
    
    #plt.imshow(img)
    ksize = 7
    # Apply each of the thresholding functions
    gradx = abs_sobel_thresh(warped, orient='x', sobel_kernel=ksize, thresh=(40, 255))
    grady = abs_sobel_thresh(warped, orient='y', sobel_kernel=ksize, thresh=(40, 255))
    mag_binary = mag_thresh(warped, sobel_kernel=ksize, mag_thresh=(40, 200))
    #plt.imshow(mag_binary)
    dir_binary = dir_threshold(warped, sobel_kernel=ksize, thresh=(0, np.pi/2))
    
    combined = np.zeros_like(dir_binary)
    combined[((gradx == 1) & (grady == 1)) | ((mag_binary == 1) & (dir_binary == 1))] = 1
    

    s_binary = np.zeros_like(combined)
    h_binary = np.zeros_like(combined)
    l_binary = np.zeros_like(combined)
    
    s_binary[(s > 50) & (s < 255)] = 1
    h_binary[(h > 50) & (h < 50)] = 1
    l_binary[(l > 10) & (l < 255)] = 1
    
    color_binary = np.zeros_like(combined)
    #color_binary[(s_binary > 0) | (combined > 0)] = 1
    color_binary[((s_binary == 1) & (r_binary == 1)) | (combined > 0)] = 1
    
    # Works color_binary[((s_binary == 1) & (combined == 1)) | ((s_binary == 1) & (h_binary == 1))
                   #  | ((s_binary == 1) & (r_binary == 1))] = 1
    
    #final_binary = np.zeros_like(color_binary)
    #final_binary[((h_binary > 0) & (l_binary > 0)) | (combined > 0)] = 1
    #final_binary[((h_binary > 0) & (s_binary > 0)) | (combined > 0)] = 1
   

    return warped, M, Minv, color_binary, undist
In [275]:
# Used to detect the lane curve in detect lanes

def lanecurvature(leftx, lefty, rightx, righty) :
    
    
    # Define conversions in x and y from pixels space to meters
    ym_per_pix = 30/720 # meters per pixel in y dimension
    xm_per_pix = 3.7/700 # meters per pixel in x dimension
    
    # Fit new polynomials to x,y in world space
    left_fit_cr = np.polyfit(ploty*ym_per_pix, leftx*xm_per_pix, 2)
    right_fit_cr = np.polyfit(ploty*ym_per_pix, rightx*xm_per_pix, 2)
    # Calculate the new radii of curvature
    left_curverad = ((1 + (2*left_fit_cr[0]*y_eval*ym_per_pix + left_fit_cr[1])**2)**1.5) / np.absolute(2*left_fit_cr[0])
    right_curverad = ((1 + (2*right_fit_cr[0]*y_eval*ym_per_pix + right_fit_cr[1])**2)**1.5) / np.absolute(2*right_fit_cr[0])
    # Now our radius of curvature is in meters
    print(left_curverad, 'm', right_curverad, 'm')
    # Example values: 632.1 m    626.2 m
    
    return left_curverad, right_curverad
In [276]:
# Lane fit function that does the histogram, sliding window, curvature fitting

def lanefit(binary_warped, img):
    # Assuming you have created a warped binary image called "binary_warped"
    # Take a histogram of the bottom half of the image
    histogram = np.sum(binary_warped[binary_warped.shape[0]//2:,:], axis=0)
    # Create an output image to draw on and  visualize the result
    out_img = np.dstack((binary_warped, binary_warped, binary_warped))*255
    # Find the peak of the left and right halves of the histogram
    # These will be the starting point for the left and right lines
    midpoint = np.int(histogram.shape[0]/2)
    leftx_base = np.argmax(histogram[:midpoint])
    rightx_base = np.argmax(histogram[midpoint:]) + midpoint

    # Choose the number of sliding windows
    nwindows = 9
    # Set height of windows
    window_height = np.int(binary_warped.shape[0]/nwindows)
    # Identify the x and y positions of all nonzero pixels in the image
    nonzero = binary_warped.nonzero()
    nonzeroy = np.array(nonzero[0])
    nonzerox = np.array(nonzero[1])
    # Current positions to be updated for each window
    leftx_current = leftx_base
    rightx_current = rightx_base
    # Set the width of the windows +/- margin
    margin = 100
    # Set minimum number of pixels found to recenter window
    minpix = 50
    # Create empty lists to receive left and right lane pixel indices
    left_lane_inds = []
    right_lane_inds = []

    # Step through the windows one by one
    for window in range(nwindows):
        # Identify window boundaries in x and y (and right and left)
        win_y_low = binary_warped.shape[0] - (window+1)*window_height
        win_y_high = binary_warped.shape[0] - window*window_height
        win_xleft_low = leftx_current - margin
        win_xleft_high = leftx_current + margin
        win_xright_low = rightx_current - margin
        win_xright_high = rightx_current + margin
        # Draw the windows on the visualization image
        cv2.rectangle(out_img,(win_xleft_low,win_y_low),(win_xleft_high,win_y_high),(0,255,0), 2) 
        cv2.rectangle(out_img,(win_xright_low,win_y_low),(win_xright_high,win_y_high),(0,255,0), 2) 
        # Identify the nonzero pixels in x and y within the window
        good_left_inds = ((nonzeroy >= win_y_low) & (nonzeroy < win_y_high) & (nonzerox >= win_xleft_low) & (nonzerox < win_xleft_high)).nonzero()[0]
        good_right_inds = ((nonzeroy >= win_y_low) & (nonzeroy < win_y_high) & (nonzerox >= win_xright_low) & (nonzerox < win_xright_high)).nonzero()[0]
        # Append these indices to the lists
        left_lane_inds.append(good_left_inds)
        right_lane_inds.append(good_right_inds)
        # If you found > minpix pixels, recenter next window on their mean position
        if len(good_left_inds) > minpix:
            leftx_current = np.int(np.mean(nonzerox[good_left_inds]))
        if len(good_right_inds) > minpix:        
            rightx_current = np.int(np.mean(nonzerox[good_right_inds]))

    # Concatenate the arrays of indices
    left_lane_inds = np.concatenate(left_lane_inds)
    right_lane_inds = np.concatenate(right_lane_inds)

    # Extract left and right line pixel positions
    leftx = nonzerox[left_lane_inds]
    lefty = nonzeroy[left_lane_inds] 
    rightx = nonzerox[right_lane_inds]
    righty = nonzeroy[right_lane_inds] 

    # Fit a second order polynomial to each
    left_fit = np.polyfit(lefty, leftx, 2)
    right_fit = np.polyfit(righty, rightx, 2)
    
    
    # Generate x and y values for plotting
    ploty = np.linspace(0, binary_warped.shape[0]-1, binary_warped.shape[0] )
    left_fitx = left_fit[0]*ploty**2 + left_fit[1]*ploty + left_fit[2]
    right_fitx = right_fit[0]*ploty**2 + right_fit[1]*ploty + right_fit[2]
    

    # Fit new polynomials to x,y in world space
    #left_curverad, right_curverad = lanecurvature(leftx, lefty, rightx, righty)
    
    out_img[nonzeroy[left_lane_inds], nonzerox[left_lane_inds]] = [255, 0, 0]
    out_img[nonzeroy[right_lane_inds], nonzerox[right_lane_inds]] = [0, 0, 255]
    

    return ploty, left_fitx, right_fitx, out_img
In [277]:
def find_3p_circle_radius(x1,y1,x2,y2,x3,y3):
    
    # source : http://www.intmath.com/applications-differentiation/8-radius-curvature.php
    m1 = (y2-y1)/(x2-x1)
    m2 = (y3-y2)/(x3-x2)
    
    xc = (m1*m2*(y1-y3)+m2*(x1+x2)-m1*(x2+x3))/(2*(m2-m1))
    yc = -(xc-(x1+x2)/2)/m1+(y1+y2)/2
    
    Radius = np.sqrt((x2-xc)*(x2-xc)+(y2-yc)*(y2-yc))
    
    return m1, m2, xc, yc, Radius
In [278]:
# Lane fit function that does the histogram, sliding window, curvature fitting

def lanefit2(binary_warped, img, Minv):
    # Assuming you have created a warped binary image called "binary_warped"
    # Take a histogram of the bottom half of the image
    histogram = np.sum(binary_warped[binary_warped.shape[0]//2:,:], axis=0)
    # Create an output image to draw on and  visualize the result
    out_img = np.dstack((binary_warped, binary_warped, binary_warped))*255
    # Find the peak of the left and right halves of the histogram
    # These will be the starting point for the left and right lines
    midpoint = np.int(histogram.shape[0]/2)
    leftx_base = np.argmax(histogram[:midpoint])
    rightx_base = np.argmax(histogram[midpoint:]) + midpoint

    # Choose the number of sliding windows
    nwindows = 9
    # Set height of windows
    window_height = np.int(binary_warped.shape[0]/nwindows)
    # Identify the x and y positions of all nonzero pixels in the image
    nonzero = binary_warped.nonzero()
    nonzeroy = np.array(nonzero[0])
    nonzerox = np.array(nonzero[1])
    # Current positions to be updated for each window
    leftx_current = leftx_base
    rightx_current = rightx_base
    # Set the width of the windows +/- margin
    margin = 100
    # Set minimum number of pixels found to recenter window
    minpix = 50
    # Create empty lists to receive left and right lane pixel indices
    left_lane_inds = []
    right_lane_inds = []

    # Step through the windows one by one
    for window in range(nwindows):
        # Identify window boundaries in x and y (and right and left)
        win_y_low = binary_warped.shape[0] - (window+1)*window_height
        win_y_high = binary_warped.shape[0] - window*window_height
        win_xleft_low = leftx_current - margin
        win_xleft_high = leftx_current + margin
        win_xright_low = rightx_current - margin
        win_xright_high = rightx_current + margin
        # Draw the windows on the visualization image
        cv2.rectangle(out_img,(win_xleft_low,win_y_low),(win_xleft_high,win_y_high),(0,255,0), 2) 
        cv2.rectangle(out_img,(win_xright_low,win_y_low),(win_xright_high,win_y_high),(0,255,0), 2) 
        # Identify the nonzero pixels in x and y within the window
        good_left_inds = ((nonzeroy >= win_y_low) & (nonzeroy < win_y_high) & (nonzerox >= win_xleft_low) & (nonzerox < win_xleft_high)).nonzero()[0]
        good_right_inds = ((nonzeroy >= win_y_low) & (nonzeroy < win_y_high) & (nonzerox >= win_xright_low) & (nonzerox < win_xright_high)).nonzero()[0]
        # Append these indices to the lists
        left_lane_inds.append(good_left_inds)
        right_lane_inds.append(good_right_inds)
        # If you found > minpix pixels, recenter next window on their mean position
        if len(good_left_inds) > minpix:
            leftx_current = np.int(np.mean(nonzerox[good_left_inds]))
        if len(good_right_inds) > minpix:        
            rightx_current = np.int(np.mean(nonzerox[good_right_inds]))

    # Concatenate the arrays of indices
    left_lane_inds = np.concatenate(left_lane_inds)
    right_lane_inds = np.concatenate(right_lane_inds)

    # Extract left and right line pixel positions
    leftx = nonzerox[left_lane_inds]
    lefty = nonzeroy[left_lane_inds] 
    rightx = nonzerox[right_lane_inds]
    righty = nonzeroy[right_lane_inds] 

    # Fit a second order polynomial to each
    left_fit = np.polyfit(lefty, leftx, 2)
    right_fit = np.polyfit(righty, rightx, 2)
    
    
    # Generate x and y values for plotting
    ploty = np.linspace(0, binary_warped.shape[0]-1, binary_warped.shape[0] )
    left_fitx = left_fit[0]*ploty**2 + left_fit[1]*ploty + left_fit[2]
    right_fitx = right_fit[0]*ploty**2 + right_fit[1]*ploty + right_fit[2]
    

    # Fit new polynomials to x,y in world space

    out_img[nonzeroy[left_lane_inds], nonzerox[left_lane_inds]] = [255, 0, 0]
    out_img[nonzeroy[right_lane_inds], nonzerox[right_lane_inds]] = [0, 0, 255]
    
    """
    New code
    """
    
    # Define conversions in x and y from pixels space to meters
    ym_per_pix = 30/720 # meters per pixel in y dimension
    xm_per_pix = 3.7/600 # meters per pixel in x dimension
    
    # Used 3 y values for max, mean and min
    y_eval_max = np.max(ploty)
    y_eval_mean = np.mean(ploty)
    y_eval_min = np.min(ploty)
    
    left_fitx_1 = left_fit[0]*y_eval_max**2 + left_fit[1]*ploty + left_fit[2]
    left_fitx_2 = left_fit[0]*y_eval_mean**2 + left_fit[1]*ploty + left_fit[2]
    left_fitx_3 = left_fit[0]*y_eval_min**2 + left_fit[1]*ploty + left_fit[2]
    
    right_fitx_1 = right_fit[0]*y_eval_max**2 + right_fit[1]*ploty + right_fit[2]
    right_fitx_2 = right_fit[0]*y_eval_mean**2 + right_fit[1]*ploty + right_fit[2]
    right_fitx_3 = right_fit[0]*y_eval_min**2 + right_fit[1]*ploty + right_fit[2]
    
    
    lm1, lm2, lxc, lyc, lradius = find_3p_circle_radius(left_fitx_1,y_eval_max,left_fitx_2,y_eval_mean,left_fitx_3,y_eval_min,)
    l_steering_angle = 5*360/lxc # assume xc <> 0, xc and radius value is very close, xc will show the direction as well
    
    
    rm1, rm2, rxc, ryc, rradius = find_3p_circle_radius(right_fitx_1,y_eval_max,right_fitx_2,y_eval_mean,right_fitx_3,y_eval_min,)
    
    r_steering_angle = 5*360/rxc # assume xc <> 0, xc and radius value is very close, xc will show the direction as well
    steering_angle = l_steering_angle + r_steering_angle
    turning_radius = (lradius+rradius)/2 # smooth out the radius
    
    # Find camera position
    #left_mean = np.mean(leftx)
    #right_mean = np.mean(rightx)
    #camera_pos = (combined.shape[1]/2)-np.mean([left_mean, right_mean])
    
    left_mean = np.mean(left_fitx_1)
    right_mean = np.mean(right_fitx_1)
    camera_pos = (combined.shape[1]/2)-np.mean([left_mean, right_mean])
    
    # Fit new polynomials to x,y in world space
    #left_fit_cr = np.polyfit(ploty*ym_per_pix, leftx*xm_per_pix, 2)
    #right_fit_cr = np.polyfit(ploty*ym_per_pix, rightx*xm_per_pix, 2)
    
    
    left_fit_cr = np.polyfit(np.array(lefty,dtype=np.float32)*ym_per_pix, \
                         np.array(leftx,dtype=np.float32)*xm_per_pix, 2)
    right_fit_cr = np.polyfit(np.array(righty,dtype=np.float32)*ym_per_pix, \
                          np.array(rightx,dtype=np.float32)*xm_per_pix, 2)
    
    # Calculate the new radii of curvature
    left_curverad = ((1 + (2*left_fit_cr[0]*y_eval_max*ym_per_pix + left_fit_cr[1])**2)**1.5) / np.absolute(2*left_fit_cr[0])
    right_curverad = ((1 + (2*right_fit_cr[0]*y_eval_max*ym_per_pix + right_fit_cr[1])**2)**1.5) / np.absolute(2*right_fit_cr[0])
    average_curverad = (left_curverad + right_curverad)/2
    # Now our radius of curvature is in meters
    print(left_curverad, 'm', right_curverad, 'm', average_curverad, 'm')
    # Example values: 632.1 m    626.2 m
    
    
    """
    New Code end
    """
    warp_zero = np.zeros_like(binary_warped).astype(np.uint8)
    #plt.imshow(warped)
    warp_zero = np.zeros_like(binary_warped).astype(np.uint8)
    color_warp = np.dstack((warp_zero, warp_zero, warp_zero))
    # Recast the x and y points into usable format for cv2.fillPoly()
    pts_left = np.array([np.transpose(np.vstack([left_fitx, ploty]))])
    pts_right = np.array([np.flipud(np.transpose(np.vstack([right_fitx, ploty])))])
    pts = np.hstack((pts_left, pts_right))
        # Draw the lane onto the warped blank image
    cv2.fillPoly(color_warp, np.int_([pts]), (0,255, 0))
    
    font = cv2.FONT_HERSHEY_SIMPLEX
    cv2.putText(img,'Camera Position' + ' [' + str(camera_pos*xm_per_pix)[:6] + '] m',(10,30), font, 1,(255,255,255),2)
    cv2.putText(img,'Curvature Radius ' + '[' + str(average_curverad)[:6] + '] m' ,(10,60), font, 1,(255,255,255),2)
    
    cv2.putText(img,'Steering Angle -VE Left, +VE Right'+'{:.6}'.format(str(abs(steering_angle))) + '] deg',(10,90), font, 1,(255,255,255),2)
 
    
    # Warp the blank back to original image space using inverse perspective matrix (Minv)
    newwarp = cv2.warpPerspective(color_warp, Minv, (img.shape[1], img.shape[0])) 
    # Combine the result with the original image
    
    result = cv2.addWeighted(img, 1.0, newwarp, 0.3, 0)
    
    return result
In [279]:
# final Image does takes the threshold perspective image, lane fitting and 
# generates the final image with inverse perspective transform after fitting the green polygon

def finalImage(warped, img, ploty, left_fitx, right_fitx, Minv):

    warp_zero = np.zeros_like(warped).astype(np.uint8)
    #plt.imshow(warped)
    warp_zero = np.zeros_like(warped).astype(np.uint8)
    color_warp = np.dstack((warp_zero, warp_zero, warp_zero))
    # Recast the x and y points into usable format for cv2.fillPoly()
    pts_left = np.array([np.transpose(np.vstack([left_fitx, ploty]))])
    pts_right = np.array([np.flipud(np.transpose(np.vstack([right_fitx, ploty])))])
    pts = np.hstack((pts_left, pts_right))
        # Draw the lane onto the warped blank image
    cv2.fillPoly(color_warp, np.int_([pts]), (0,255, 0))
    
    # Warp the blank back to original image space using inverse perspective matrix (Minv)
    newwarp = cv2.warpPerspective(color_warp, Minv, (img.shape[1], img.shape[0])) 
    # Combine the result with the original image
    result = cv2.addWeighted(img, 1.0, newwarp, 0.3, 0)
    return result
In [280]:
img = mpimg.imread('test/25.jpg')
#plt.imshow(img)
warped, M, Minv, binary_warped, undist = pipeline3(img)
#plt.imshow(color_binary)
Image shape: (720, 1280, 3)
In [281]:
plt.imshow(binary_warped, cmap='gray')
Out[281]:
<matplotlib.image.AxesImage at 0x12983ac50>
In [282]:
# Original image and S channel combined with Perspective view

f, (ax1, ax2) = plt.subplots(1, 2, figsize=(24, 9))
f.tight_layout()
ax1.imshow(warped)
ax1.set_title('Original Image', fontsize=50)
ax2.imshow(binary_warped, cmap='gray')
ax2.set_title('S channel + Combined Image', fontsize=50)
plt.subplots_adjust(left=0., right=1, top=0.9, bottom=0.)
In [283]:
# Histogram showing the peak points in the lane

hist = np.sum(binary_warped[binary_warped.shape[0]//2:,:], axis=0)
plt.plot(hist)
Out[283]:
[<matplotlib.lines.Line2D at 0x12f39d3c8>]
In [284]:
# Test perspective image

warped2, M, Minv, undist = corners_unwarp(img, mtx, dist)
plt.imshow(warped2)
Image shape: (720, 1280, 3)
Out[284]:
<matplotlib.image.AxesImage at 0x1298e1cc0>
In [285]:
# Test lanefit

ploty, left_fitx, right_fitx, out_img = lanefit(binary_warped, img)
In [286]:
# Test final Image

result = finalImage(binary_warped, img, ploty, left_fitx, right_fitx, Minv)
plt.imshow(result)
Out[286]:
<matplotlib.image.AxesImage at 0x135a9ac88>
In [287]:
# This is main function, that gets the original image and process
# Pipeline, lanefit and final processing 

def process_image(img):
    warped, M, Minv, binary_warped, undist = pipeline3(img)
    ploty, left_fitx, right_fitx, out_img = lanefit(binary_warped, img)
    result = finalImage(binary_warped, img, ploty, left_fitx, right_fitx, Minv)
    return result
    
In [288]:
img2 = mpimg.imread('test_images/test1.jpg')
result2 = process_image(img2)
plt.imshow(result2)
Image shape: (720, 1280, 3)
Out[288]:
<matplotlib.image.AxesImage at 0x1330f6e10>
In [289]:
# Showing the original image and Final Image image for a test image

f, (ax1, ax2) = plt.subplots(1, 2, figsize=(24, 9))
f.tight_layout()
ax1.imshow(img2)
ax1.set_title('Original Image', fontsize=50)
ax2.imshow(result2, cmap='gray')
ax2.set_title('Final Image', fontsize=50)
plt.subplots_adjust(left=0., right=1, top=0.9, bottom=0.)
In [290]:
img2 = mpimg.imread('test/24.jpg')
plt.imshow(img2)
Out[290]:
<matplotlib.image.AxesImage at 0x1298de438>
In [291]:
def process_image2(img) :
    
    warped, M, Minv, binary_warped, undist = pipeline3(img)
    result = lanefit2(binary_warped, img, Minv)
   
    return result
In [292]:
result = process_image2(img2)
plt.imshow(result)
Image shape: (720, 1280, 3)
14018.5534874 m 186.582099002 m 7102.5677932 m
Out[292]:
<matplotlib.image.AxesImage at 0x129b04a90>
In [53]:
# Function to read the video file from repository
# Generate the pipeline video file

clip = VideoFileClip("project_video.mp4")
video_out = "project_video_out5.mp4"

video_cap = clip.fl_image(process_image2)
%time video_cap.write_videofile(video_out, audio=False)
Image shape: (720, 1280, 3)
561.431030001 m 2052.63376719 m 1307.0323986 m
[MoviePy] >>>> Building video project_video_out5.mp4
[MoviePy] Writing video project_video_out5.mp4
  0%|          | 0/1261 [00:00<?, ?it/s]
Image shape: (720, 1280, 3)
  0%|          | 1/1261 [00:00<07:04,  2.97it/s]
561.431030001 m 2052.63376719 m 1307.0323986 m
Image shape: (720, 1280, 3)
  0%|          | 2/1261 [00:00<06:59,  3.00it/s]
549.246000454 m 1690.81433673 m 1120.03016859 m
Image shape: (720, 1280, 3)
  0%|          | 3/1261 [00:00<06:56,  3.02it/s]
515.431765289 m 446.424255867 m 480.928010578 m
Image shape: (720, 1280, 3)
  0%|          | 4/1261 [00:01<06:55,  3.02it/s]
454.444245274 m 630.720889632 m 542.582567453 m
Image shape: (720, 1280, 3)
  0%|          | 5/1261 [00:01<06:56,  3.02it/s]
504.241284201 m 672.6385672 m 588.4399257 m
Image shape: (720, 1280, 3)
  0%|          | 6/1261 [00:01<06:56,  3.01it/s]
486.515740069 m 671.357991608 m 578.936865838 m
Image shape: (720, 1280, 3)
  1%|          | 7/1261 [00:02<06:54,  3.02it/s]
490.596747004 m 594.182934943 m 542.389840973 m
Image shape: (720, 1280, 3)
  1%|          | 8/1261 [00:02<06:53,  3.03it/s]
478.769783401 m 583.334251105 m 531.052017253 m
Image shape: (720, 1280, 3)
  1%|          | 9/1261 [00:02<06:54,  3.02it/s]
491.731213204 m 568.324517554 m 530.027865379 m
Image shape: (720, 1280, 3)
  1%|          | 10/1261 [00:03<06:55,  3.01it/s]
494.138762229 m 599.279380515 m 546.709071372 m
Image shape: (720, 1280, 3)
  1%|          | 11/1261 [00:03<06:53,  3.02it/s]
531.261558762 m 547.846099201 m 539.553828982 m
Image shape: (720, 1280, 3)
  1%|          | 12/1261 [00:03<06:52,  3.02it/s]
529.642248173 m 799.285955565 m 664.464101869 m
Image shape: (720, 1280, 3)
  1%|          | 13/1261 [00:04<06:52,  3.03it/s]
553.653082463 m 616.814280519 m 585.233681491 m
Image shape: (720, 1280, 3)
  1%|          | 14/1261 [00:04<06:52,  3.03it/s]
582.500084313 m 463.041191846 m 522.77063808 m
Image shape: (720, 1280, 3)
  1%|          | 15/1261 [00:04<06:50,  3.03it/s]
584.310879136 m 404.025750882 m 494.168315009 m
Image shape: (720, 1280, 3)
  1%|▏         | 16/1261 [00:05<06:51,  3.03it/s]
580.086395349 m 764.975561922 m 672.530978635 m
Image shape: (720, 1280, 3)
  1%|▏         | 17/1261 [00:05<06:51,  3.02it/s]
649.71859418 m 1100.11991201 m 874.919253096 m
Image shape: (720, 1280, 3)
  1%|▏         | 18/1261 [00:05<06:51,  3.02it/s]
664.39028145 m 690.371564679 m 677.380923064 m
Image shape: (720, 1280, 3)
  2%|▏         | 19/1261 [00:06<06:53,  3.00it/s]
680.171716571 m 577.185247008 m 628.678481789 m
Image shape: (720, 1280, 3)
  2%|▏         | 20/1261 [00:06<06:52,  3.01it/s]
746.074393829 m 574.835805147 m 660.455099488 m
Image shape: (720, 1280, 3)
  2%|▏         | 21/1261 [00:06<06:51,  3.02it/s]
751.444686078 m 570.764076382 m 661.10438123 m
Image shape: (720, 1280, 3)
  2%|▏         | 22/1261 [00:07<06:51,  3.01it/s]
807.435364836 m 780.42638924 m 793.930877038 m
Image shape: (720, 1280, 3)
  2%|▏         | 23/1261 [00:07<06:50,  3.02it/s]
751.7348729 m 996.210472633 m 873.972672766 m
Image shape: (720, 1280, 3)
  2%|▏         | 24/1261 [00:07<06:48,  3.03it/s]
722.450766782 m 790.326360318 m 756.38856355 m
Image shape: (720, 1280, 3)
  2%|▏         | 25/1261 [00:08<06:48,  3.02it/s]
686.833600954 m 1038.9632453 m 862.898423125 m
Image shape: (720, 1280, 3)
  2%|▏         | 26/1261 [00:08<06:46,  3.04it/s]
716.904291185 m 283.727144058 m 500.315717622 m
Image shape: (720, 1280, 3)
  2%|▏         | 27/1261 [00:08<06:52,  2.99it/s]
669.367175655 m 721.842664462 m 695.604920059 m
Image shape: (720, 1280, 3)
  2%|▏         | 28/1261 [00:09<06:48,  3.02it/s]
650.785556316 m 1430.79959098 m 1040.79257365 m
Image shape: (720, 1280, 3)
  2%|▏         | 29/1261 [00:10<11:38,  1.76it/s]
639.430220498 m 915.327302992 m 777.378761745 m
Image shape: (720, 1280, 3)
  2%|▏         | 30/1261 [00:10<10:10,  2.02it/s]
551.923313805 m 637.761218537 m 594.842266171 m
Image shape: (720, 1280, 3)
  2%|▏         | 31/1261 [00:11<09:07,  2.25it/s]
531.952215748 m 689.367942485 m 610.660079117 m
Image shape: (720, 1280, 3)
  3%|▎         | 32/1261 [00:11<08:22,  2.45it/s]
499.763417783 m 477.359802307 m 488.561610045 m
Image shape: (720, 1280, 3)
  3%|▎         | 33/1261 [00:11<07:51,  2.60it/s]
508.254223991 m 489.091990856 m 498.673107423 m
Image shape: (720, 1280, 3)
  3%|▎         | 34/1261 [00:12<07:30,  2.72it/s]
464.562220823 m 484.560943349 m 474.561582086 m
Image shape: (720, 1280, 3)
  3%|▎         | 35/1261 [00:12<07:17,  2.80it/s]
479.269291211 m 501.125611163 m 490.197451187 m
Image shape: (720, 1280, 3)
  3%|▎         | 36/1261 [00:12<07:06,  2.87it/s]
425.792498573 m 458.832236062 m 442.312367317 m
Image shape: (720, 1280, 3)
  3%|▎         | 37/1261 [00:13<07:08,  2.86it/s]
432.612274208 m 282.916983033 m 357.764628621 m
Image shape: (720, 1280, 3)
  3%|▎         | 38/1261 [00:13<07:09,  2.85it/s]
389.254637777 m 282.482275438 m 335.868456607 m
Image shape: (720, 1280, 3)
  3%|▎         | 39/1261 [00:13<07:01,  2.90it/s]
373.785363132 m 232.803005126 m 303.294184129 m
Image shape: (720, 1280, 3)
  3%|▎         | 40/1261 [00:14<06:54,  2.94it/s]
395.212096984 m 238.212794452 m 316.712445718 m
Image shape: (720, 1280, 3)
  3%|▎         | 41/1261 [00:14<06:51,  2.97it/s]
390.425648167 m 256.421934137 m 323.423791152 m
Image shape: (720, 1280, 3)
  3%|▎         | 42/1261 [00:14<06:47,  2.99it/s]
407.557132567 m 340.499288948 m 374.028210758 m
Image shape: (720, 1280, 3)
  3%|▎         | 43/1261 [00:15<06:49,  2.98it/s]
385.965484178 m 617.235248731 m 501.600366454 m
Image shape: (720, 1280, 3)
  3%|▎         | 44/1261 [00:15<06:47,  2.99it/s]
398.907050207 m 523.792189714 m 461.34961996 m
Image shape: (720, 1280, 3)
  4%|▎         | 45/1261 [00:15<06:44,  3.01it/s]
422.892135066 m 500.978202508 m 461.935168787 m
Image shape: (720, 1280, 3)
  4%|▎         | 46/1261 [00:16<06:41,  3.03it/s]
435.057653662 m 525.979228439 m 480.51844105 m
Image shape: (720, 1280, 3)
  4%|▎         | 47/1261 [00:16<06:41,  3.02it/s]
463.628896399 m 525.235897636 m 494.432397017 m
Image shape: (720, 1280, 3)
  4%|▍         | 48/1261 [00:16<06:41,  3.02it/s]
470.918044138 m 518.843844417 m 494.880944278 m
Image shape: (720, 1280, 3)
  4%|▍         | 49/1261 [00:17<06:39,  3.03it/s]
504.080136818 m 601.306213725 m 552.693175272 m
Image shape: (720, 1280, 3)
  4%|▍         | 50/1261 [00:17<06:39,  3.03it/s]
544.954846346 m 332.651672008 m 438.803259177 m
Image shape: (720, 1280, 3)
  4%|▍         | 51/1261 [00:17<06:40,  3.02it/s]
555.596551785 m 354.91534003 m 455.255945908 m
Image shape: (720, 1280, 3)
  4%|▍         | 52/1261 [00:18<06:40,  3.02it/s]
590.136951728 m 327.600384685 m 458.868668206 m
Image shape: (720, 1280, 3)
  4%|▍         | 53/1261 [00:18<06:41,  3.01it/s]
604.456101421 m 319.238632616 m 461.847367018 m
Image shape: (720, 1280, 3)
  4%|▍         | 54/1261 [00:18<06:41,  3.00it/s]
620.539891166 m 361.874775842 m 491.207333504 m
Image shape: (720, 1280, 3)
  4%|▍         | 55/1261 [00:19<06:49,  2.95it/s]
728.249408456 m 625.275287413 m 676.762347935 m
Image shape: (720, 1280, 3)
  4%|▍         | 56/1261 [00:19<06:47,  2.96it/s]
778.66675482 m 719.493451145 m 749.080102982 m
Image shape: (720, 1280, 3)
  5%|▍         | 57/1261 [00:19<06:45,  2.97it/s]
836.832575001 m 474.812805805 m 655.822690403 m
Image shape: (720, 1280, 3)
  5%|▍         | 58/1261 [00:20<06:42,  2.99it/s]
781.709332711 m 432.994008825 m 607.351670768 m
Image shape: (720, 1280, 3)
  5%|▍         | 59/1261 [00:20<06:41,  2.99it/s]
689.725332027 m 386.340795446 m 538.033063736 m
Image shape: (720, 1280, 3)
  5%|▍         | 60/1261 [00:20<06:40,  3.00it/s]
689.895917227 m 353.671545094 m 521.78373116 m
Image shape: (720, 1280, 3)
  5%|▍         | 61/1261 [00:21<06:53,  2.90it/s]
622.712733914 m 353.175073248 m 487.943903581 m
Image shape: (720, 1280, 3)
  5%|▍         | 62/1261 [00:21<06:57,  2.87it/s]
618.639480092 m 374.173143413 m 496.406311752 m
Image shape: (720, 1280, 3)
  5%|▍         | 63/1261 [00:21<06:57,  2.87it/s]
589.805985176 m 282.859430222 m 436.332707699 m
Image shape: (720, 1280, 3)
  5%|▌         | 64/1261 [00:22<06:51,  2.91it/s]
575.23175164 m 410.255044313 m 492.743397977 m
Image shape: (720, 1280, 3)
  5%|▌         | 65/1261 [00:22<06:48,  2.93it/s]
522.70724286 m 482.631934904 m 502.669588882 m
Image shape: (720, 1280, 3)
  5%|▌         | 66/1261 [00:22<06:44,  2.96it/s]
536.102728117 m 498.382939657 m 517.242833887 m
Image shape: (720, 1280, 3)
  5%|▌         | 67/1261 [00:23<06:41,  2.98it/s]
621.122044279 m 808.131832338 m 714.626938308 m
Image shape: (720, 1280, 3)
  5%|▌         | 68/1261 [00:23<06:41,  2.97it/s]
590.072975702 m 890.179989985 m 740.126482843 m
Image shape: (720, 1280, 3)
  5%|▌         | 69/1261 [00:23<06:40,  2.98it/s]
613.214154184 m 494.331497608 m 553.772825896 m
Image shape: (720, 1280, 3)
  6%|▌         | 70/1261 [00:24<06:40,  2.98it/s]
626.248000371 m 465.541549357 m 545.894774864 m
Image shape: (720, 1280, 3)
  6%|▌         | 71/1261 [00:24<06:39,  2.98it/s]
649.883898984 m 468.120620356 m 559.00225967 m
Image shape: (720, 1280, 3)
  6%|▌         | 72/1261 [00:24<06:40,  2.97it/s]
728.562281072 m 528.584455153 m 628.573368112 m
Image shape: (720, 1280, 3)
  6%|▌         | 73/1261 [00:25<06:40,  2.97it/s]
811.770108732 m 556.729264358 m 684.249686545 m
Image shape: (720, 1280, 3)
  6%|▌         | 74/1261 [00:25<06:39,  2.97it/s]
879.636561183 m 449.020759803 m 664.328660493 m
Image shape: (720, 1280, 3)
  6%|▌         | 75/1261 [00:25<06:36,  2.99it/s]
972.434720882 m 360.919633711 m 666.677177296 m
Image shape: (720, 1280, 3)
  6%|▌         | 76/1261 [00:26<06:38,  2.98it/s]
889.515421077 m 343.840790777 m 616.678105927 m
Image shape: (720, 1280, 3)
  6%|▌         | 77/1261 [00:26<06:37,  2.98it/s]
1007.43522809 m 325.869009448 m 666.652118767 m
Image shape: (720, 1280, 3)
  6%|▌         | 78/1261 [00:26<06:42,  2.94it/s]
1312.43976455 m 310.089662547 m 811.264713549 m
Image shape: (720, 1280, 3)
  6%|▋         | 79/1261 [00:27<06:41,  2.94it/s]
1331.29005549 m 347.266704729 m 839.278380111 m
Image shape: (720, 1280, 3)
  6%|▋         | 80/1261 [00:27<06:42,  2.93it/s]
1410.03645557 m 644.142601779 m 1027.08952867 m
Image shape: (720, 1280, 3)
  6%|▋         | 81/1261 [00:27<06:39,  2.95it/s]
1495.33049237 m 581.344997558 m 1038.33774496 m
Image shape: (720, 1280, 3)
  7%|▋         | 82/1261 [00:28<06:38,  2.96it/s]
1369.50034012 m 510.668915684 m 940.084627903 m
Image shape: (720, 1280, 3)
  7%|▋         | 83/1261 [00:28<06:37,  2.96it/s]
1197.46726192 m 466.36850863 m 831.917885275 m
Image shape: (720, 1280, 3)
  7%|▋         | 84/1261 [00:28<06:37,  2.96it/s]
1270.49013792 m 465.347700285 m 867.918919101 m
Image shape: (720, 1280, 3)
  7%|▋         | 85/1261 [00:29<06:35,  2.97it/s]
1161.54320873 m 418.248561098 m 789.895884915 m
Image shape: (720, 1280, 3)
  7%|▋         | 86/1261 [00:29<06:36,  2.96it/s]
1008.37496877 m 404.507771004 m 706.441369887 m
Image shape: (720, 1280, 3)
  7%|▋         | 87/1261 [00:29<06:35,  2.97it/s]
771.555654795 m 379.932639103 m 575.744146949 m
Image shape: (720, 1280, 3)
  7%|▋         | 88/1261 [00:30<06:35,  2.97it/s]
742.755394081 m 370.198983204 m 556.477188643 m
Image shape: (720, 1280, 3)
  7%|▋         | 89/1261 [00:30<06:35,  2.97it/s]
619.28634159 m 287.342201309 m 453.31427145 m
Image shape: (720, 1280, 3)
  7%|▋         | 90/1261 [00:30<06:34,  2.97it/s]
546.851187039 m 392.134479767 m 469.492833403 m
Image shape: (720, 1280, 3)
  7%|▋         | 91/1261 [00:31<06:34,  2.97it/s]
553.770364348 m 497.640541402 m 525.705452875 m
Image shape: (720, 1280, 3)
  7%|▋         | 92/1261 [00:31<06:33,  2.97it/s]
559.486607642 m 651.217929081 m 605.352268362 m
Image shape: (720, 1280, 3)
  7%|▋         | 93/1261 [00:31<06:34,  2.96it/s]
558.910509429 m 627.436993605 m 593.173751517 m
Image shape: (720, 1280, 3)
  7%|▋         | 94/1261 [00:32<06:30,  2.98it/s]
562.306178299 m 643.148665459 m 602.727421879 m
Image shape: (720, 1280, 3)
  8%|▊         | 95/1261 [00:32<06:31,  2.98it/s]
579.948496864 m 613.884312942 m 596.916404903 m
Image shape: (720, 1280, 3)
  8%|▊         | 96/1261 [00:32<06:32,  2.97it/s]
578.050601528 m 491.232769139 m 534.641685334 m
Image shape: (720, 1280, 3)
  8%|▊         | 97/1261 [00:33<06:31,  2.98it/s]
598.442567372 m 461.553735711 m 529.998151541 m
Image shape: (720, 1280, 3)
  8%|▊         | 98/1261 [00:33<06:32,  2.96it/s]
580.887918244 m 491.901919178 m 536.394918711 m
Image shape: (720, 1280, 3)
  8%|▊         | 99/1261 [00:33<06:32,  2.96it/s]
600.378255053 m 428.513022412 m 514.445638732 m
Image shape: (720, 1280, 3)
  8%|▊         | 100/1261 [00:34<06:32,  2.96it/s]
630.215919701 m 461.940733582 m 546.078326642 m
Image shape: (720, 1280, 3)
  8%|▊         | 101/1261 [00:34<06:31,  2.97it/s]
614.079618036 m 525.675046227 m 569.877332132 m
Image shape: (720, 1280, 3)
  8%|▊         | 102/1261 [00:34<06:31,  2.96it/s]
603.559726449 m 438.31850023 m 520.93911334 m
Image shape: (720, 1280, 3)
  8%|▊         | 103/1261 [00:35<06:29,  2.97it/s]
564.552455156 m 284.336645492 m 424.444550324 m
Image shape: (720, 1280, 3)
  8%|▊         | 104/1261 [00:35<06:29,  2.97it/s]
620.785200556 m 452.297246775 m 536.541223665 m
Image shape: (720, 1280, 3)
  8%|▊         | 105/1261 [00:35<06:31,  2.96it/s]
598.66580399 m 506.953712146 m 552.809758068 m
Image shape: (720, 1280, 3)
  8%|▊         | 106/1261 [00:36<06:29,  2.96it/s]
703.170396976 m 535.051468873 m 619.110932924 m
Image shape: (720, 1280, 3)
  8%|▊         | 107/1261 [00:36<06:29,  2.97it/s]
706.322846217 m 610.205970283 m 658.26440825 m
Image shape: (720, 1280, 3)
  9%|▊         | 108/1261 [00:36<06:28,  2.97it/s]
575.267910735 m 884.842210692 m 730.055060713 m
Image shape: (720, 1280, 3)
  9%|▊         | 109/1261 [00:37<06:26,  2.98it/s]
565.373260608 m 857.93579201 m 711.654526309 m
Image shape: (720, 1280, 3)
  9%|▊         | 110/1261 [00:37<06:25,  2.99it/s]
612.21253073 m 472.192417322 m 542.202474026 m
Image shape: (720, 1280, 3)
  9%|▉         | 111/1261 [00:37<06:25,  2.98it/s]
544.470715697 m 430.531936286 m 487.501325991 m
Image shape: (720, 1280, 3)
  9%|▉         | 112/1261 [00:38<06:25,  2.98it/s]
629.835233518 m 439.10946328 m 534.472348399 m
Image shape: (720, 1280, 3)
  9%|▉         | 113/1261 [00:38<06:25,  2.98it/s]
531.193208413 m 429.706877168 m 480.450042791 m
Image shape: (720, 1280, 3)
  9%|▉         | 114/1261 [00:38<06:27,  2.96it/s]
512.83044372 m 406.264059062 m 459.547251391 m
Image shape: (720, 1280, 3)
  9%|▉         | 115/1261 [00:39<06:26,  2.96it/s]
471.869341099 m 328.517854047 m 400.193597573 m
Image shape: (720, 1280, 3)
  9%|▉         | 116/1261 [00:39<06:24,  2.98it/s]
472.259363309 m 400.424306593 m 436.341834951 m
Image shape: (720, 1280, 3)
  9%|▉         | 117/1261 [00:39<06:23,  2.99it/s]
467.796493232 m 315.982897059 m 391.889695146 m
Image shape: (720, 1280, 3)
  9%|▉         | 118/1261 [00:40<06:22,  2.99it/s]
470.846326817 m 518.855095103 m 494.85071096 m
Image shape: (720, 1280, 3)
  9%|▉         | 119/1261 [00:40<06:23,  2.98it/s]
457.596539093 m 423.569269768 m 440.582904431 m
Image shape: (720, 1280, 3)
 10%|▉         | 120/1261 [00:40<06:24,  2.97it/s]
490.880773633 m 404.307673207 m 447.59422342 m
Image shape: (720, 1280, 3)
 10%|▉         | 121/1261 [00:41<06:23,  2.97it/s]
485.387381343 m 435.431274831 m 460.409328087 m
Image shape: (720, 1280, 3)
 10%|▉         | 122/1261 [00:41<06:23,  2.97it/s]
445.341588548 m 442.418505937 m 443.880047242 m
Image shape: (720, 1280, 3)
 10%|▉         | 123/1261 [00:41<06:24,  2.96it/s]
430.264575685 m 377.837301524 m 404.050938604 m
Image shape: (720, 1280, 3)
 10%|▉         | 124/1261 [00:42<06:22,  2.97it/s]
441.362325879 m 355.533009539 m 398.447667709 m
Image shape: (720, 1280, 3)
 10%|▉         | 125/1261 [00:42<06:22,  2.97it/s]
478.609643206 m 270.890916342 m 374.750279774 m
Image shape: (720, 1280, 3)
 10%|▉         | 126/1261 [00:42<06:23,  2.96it/s]
459.582953559 m 294.992322956 m 377.287638258 m
Image shape: (720, 1280, 3)
 10%|█         | 127/1261 [00:43<06:25,  2.94it/s]
452.688074668 m 294.596027472 m 373.64205107 m
Image shape: (720, 1280, 3)
 10%|█         | 128/1261 [00:43<06:25,  2.94it/s]
467.337467699 m 348.544703612 m 407.941085656 m
Image shape: (720, 1280, 3)
 10%|█         | 129/1261 [00:44<06:22,  2.96it/s]
468.130825903 m 308.521416533 m 388.326121218 m
Image shape: (720, 1280, 3)
 10%|█         | 130/1261 [00:44<06:23,  2.95it/s]
534.473183287 m 318.711429271 m 426.592306279 m
Image shape: (720, 1280, 3)
 10%|█         | 131/1261 [00:44<06:20,  2.97it/s]
515.169737712 m 458.935840624 m 487.052789168 m
Image shape: (720, 1280, 3)
 10%|█         | 132/1261 [00:45<06:21,  2.96it/s]
501.072648094 m 455.690513165 m 478.38158063 m
Image shape: (720, 1280, 3)
 11%|█         | 133/1261 [00:45<06:22,  2.95it/s]
529.410074424 m 448.486367865 m 488.948221145 m
Image shape: (720, 1280, 3)
 11%|█         | 134/1261 [00:45<06:23,  2.94it/s]
515.119095284 m 395.132978777 m 455.126037031 m
Image shape: (720, 1280, 3)
 11%|█         | 135/1261 [00:46<06:22,  2.95it/s]
513.763656622 m 407.227614399 m 460.49563551 m
Image shape: (720, 1280, 3)
 11%|█         | 136/1261 [00:46<06:20,  2.96it/s]
559.01154053 m 476.402190214 m 517.706865372 m
Image shape: (720, 1280, 3)
 11%|█         | 137/1261 [00:46<06:23,  2.93it/s]
604.831059297 m 546.844877346 m 575.837968322 m
Image shape: (720, 1280, 3)
 11%|█         | 138/1261 [00:47<06:30,  2.88it/s]
613.963282611 m 642.403078543 m 628.183180577 m
Image shape: (720, 1280, 3)
 11%|█         | 139/1261 [00:47<06:32,  2.86it/s]
596.792767108 m 353.783960176 m 475.288363642 m
Image shape: (720, 1280, 3)
 11%|█         | 140/1261 [00:47<06:27,  2.89it/s]
602.025215587 m 402.824108752 m 502.42466217 m
Image shape: (720, 1280, 3)
 11%|█         | 141/1261 [00:48<06:25,  2.90it/s]
643.556222718 m 459.138228779 m 551.347225749 m
Image shape: (720, 1280, 3)
 11%|█▏        | 142/1261 [00:48<06:23,  2.91it/s]
690.220069765 m 458.240633497 m 574.230351631 m
Image shape: (720, 1280, 3)
 11%|█▏        | 143/1261 [00:48<06:27,  2.88it/s]
643.823279798 m 766.842376377 m 705.332828087 m
Image shape: (720, 1280, 3)
 11%|█▏        | 144/1261 [00:49<06:30,  2.86it/s]
662.965152298 m 706.301922099 m 684.633537199 m
Image shape: (720, 1280, 3)
 11%|█▏        | 145/1261 [00:49<06:26,  2.89it/s]
685.29489427 m 645.520322793 m 665.407608532 m
Image shape: (720, 1280, 3)
 12%|█▏        | 146/1261 [00:49<06:22,  2.91it/s]
806.929533867 m 540.038730398 m 673.484132132 m
Image shape: (720, 1280, 3)
 12%|█▏        | 147/1261 [00:50<06:21,  2.92it/s]
684.199142768 m 650.187835377 m 667.193489072 m
Image shape: (720, 1280, 3)
 12%|█▏        | 148/1261 [00:50<06:18,  2.94it/s]
674.589564271 m 465.597401384 m 570.093482828 m
Image shape: (720, 1280, 3)
 12%|█▏        | 149/1261 [00:50<06:15,  2.96it/s]
688.535598305 m 597.846144417 m 643.190871361 m
Image shape: (720, 1280, 3)
 12%|█▏        | 150/1261 [00:51<06:12,  2.98it/s]
735.112771215 m 329.530633306 m 532.32170226 m
Image shape: (720, 1280, 3)
 12%|█▏        | 151/1261 [00:51<06:12,  2.98it/s]
649.632366503 m 358.185079035 m 503.908722769 m
Image shape: (720, 1280, 3)
 12%|█▏        | 152/1261 [00:51<06:12,  2.98it/s]
718.761740094 m 283.922406974 m 501.342073534 m
Image shape: (720, 1280, 3)
 12%|█▏        | 153/1261 [00:52<06:12,  2.98it/s]
705.801611031 m 289.021442939 m 497.411526985 m
Image shape: (720, 1280, 3)
 12%|█▏        | 154/1261 [00:52<06:13,  2.97it/s]
762.536527805 m 308.830195658 m 535.683361731 m
Image shape: (720, 1280, 3)
 12%|█▏        | 155/1261 [00:52<06:13,  2.96it/s]
756.480902072 m 401.461017199 m 578.970959635 m
Image shape: (720, 1280, 3)
 12%|█▏        | 156/1261 [00:53<06:23,  2.88it/s]
740.466329768 m 803.750231954 m 772.108280861 m
Image shape: (720, 1280, 3)
 12%|█▏        | 157/1261 [00:53<06:22,  2.89it/s]
738.428992279 m 645.469293099 m 691.949142689 m
Image shape: (720, 1280, 3)
 13%|█▎        | 158/1261 [00:53<06:18,  2.91it/s]
670.089378561 m 537.342242132 m 603.715810346 m
Image shape: (720, 1280, 3)
 13%|█▎        | 159/1261 [00:54<06:14,  2.94it/s]
644.962345184 m 540.475200947 m 592.718773066 m
Image shape: (720, 1280, 3)
 13%|█▎        | 160/1261 [00:54<06:34,  2.79it/s]
580.458320333 m 491.16136894 m 535.809844637 m
Image shape: (720, 1280, 3)
 13%|█▎        | 161/1261 [00:54<06:26,  2.84it/s]
599.050383192 m 368.969935818 m 484.010159505 m
Image shape: (720, 1280, 3)
 13%|█▎        | 162/1261 [00:55<06:21,  2.88it/s]
598.080628982 m 626.547483374 m 612.314056178 m
Image shape: (720, 1280, 3)
 13%|█▎        | 163/1261 [00:55<06:18,  2.90it/s]
601.627635132 m 417.351166947 m 509.489401039 m
Image shape: (720, 1280, 3)
 13%|█▎        | 164/1261 [00:56<06:16,  2.92it/s]
588.957230777 m 371.894500112 m 480.425865444 m
Image shape: (720, 1280, 3)
 13%|█▎        | 165/1261 [00:56<06:13,  2.93it/s]
571.306658323 m 401.78930635 m 486.547982337 m
Image shape: (720, 1280, 3)
 13%|█▎        | 166/1261 [00:56<06:15,  2.92it/s]
548.000525606 m 495.849718984 m 521.925122295 m
Image shape: (720, 1280, 3)
 13%|█▎        | 167/1261 [00:57<06:11,  2.94it/s]
545.844460626 m 508.568461432 m 527.206461029 m
Image shape: (720, 1280, 3)
 13%|█▎        | 168/1261 [00:57<06:10,  2.95it/s]
607.491082293 m 833.747749076 m 720.619415685 m
Image shape: (720, 1280, 3)
 13%|█▎        | 169/1261 [00:57<06:08,  2.96it/s]
661.553576807 m 918.879536965 m 790.216556886 m
Image shape: (720, 1280, 3)
 13%|█▎        | 170/1261 [00:58<06:08,  2.96it/s]
704.88389357 m 699.139948476 m 702.011921023 m
Image shape: (720, 1280, 3)
 14%|█▎        | 171/1261 [00:58<06:08,  2.96it/s]
755.899434792 m 821.952125493 m 788.925780143 m
Image shape: (720, 1280, 3)
 14%|█▎        | 172/1261 [00:58<06:06,  2.97it/s]
765.370371482 m 674.835567867 m 720.102969674 m
Image shape: (720, 1280, 3)
 14%|█▎        | 173/1261 [00:59<06:04,  2.98it/s]
725.395963707 m 637.586764386 m 681.491364046 m
Image shape: (720, 1280, 3)
 14%|█▍        | 174/1261 [00:59<06:05,  2.97it/s]
664.07147106 m 517.72180457 m 590.896637815 m
Image shape: (720, 1280, 3)
 14%|█▍        | 175/1261 [00:59<06:04,  2.98it/s]
625.424181322 m 447.960736849 m 536.692459086 m
Image shape: (720, 1280, 3)
 14%|█▍        | 176/1261 [01:00<06:03,  2.98it/s]
564.687439175 m 291.717135878 m 428.202287526 m
Image shape: (720, 1280, 3)
 14%|█▍        | 177/1261 [01:00<06:01,  3.00it/s]
632.621132778 m 281.764466557 m 457.192799668 m
Image shape: (720, 1280, 3)
 14%|█▍        | 178/1261 [01:00<05:59,  3.01it/s]
635.432043404 m 289.120587474 m 462.276315439 m
Image shape: (720, 1280, 3)
 14%|█▍        | 179/1261 [01:01<05:58,  3.02it/s]
615.792607667 m 322.69835167 m 469.245479669 m
Image shape: (720, 1280, 3)
 14%|█▍        | 180/1261 [01:01<05:59,  3.00it/s]
597.841842335 m 415.941574749 m 506.891708542 m
Image shape: (720, 1280, 3)
 14%|█▍        | 181/1261 [01:01<06:03,  2.97it/s]
527.040059318 m 351.239469129 m 439.139764223 m
Image shape: (720, 1280, 3)
 14%|█▍        | 182/1261 [01:02<06:04,  2.96it/s]
521.411033379 m 373.302649762 m 447.356841571 m
Image shape: (720, 1280, 3)
 15%|█▍        | 183/1261 [01:02<06:05,  2.95it/s]
469.31106353 m 369.675550944 m 419.493307237 m
Image shape: (720, 1280, 3)
 15%|█▍        | 184/1261 [01:02<06:03,  2.97it/s]
479.095657423 m 334.423398689 m 406.759528056 m
Image shape: (720, 1280, 3)
 15%|█▍        | 185/1261 [01:03<06:02,  2.97it/s]
423.393223917 m 323.78377555 m 373.588499733 m
Image shape: (720, 1280, 3)
 15%|█▍        | 186/1261 [01:03<05:59,  2.99it/s]
365.877194813 m 281.394156469 m 323.635675641 m
Image shape: (720, 1280, 3)
 15%|█▍        | 187/1261 [01:03<05:58,  2.99it/s]
373.048576417 m 308.62030632 m 340.834441368 m
Image shape: (720, 1280, 3)
 15%|█▍        | 188/1261 [01:04<05:57,  3.00it/s]
355.757527258 m 309.862326019 m 332.809926638 m
Image shape: (720, 1280, 3)
 15%|█▍        | 189/1261 [01:04<05:55,  3.01it/s]
403.044777733 m 260.272073648 m 331.658425691 m
Image shape: (720, 1280, 3)
 15%|█▌        | 190/1261 [01:04<05:54,  3.02it/s]
374.493349081 m 310.071788435 m 342.282568758 m
Image shape: (720, 1280, 3)
 15%|█▌        | 191/1261 [01:05<05:54,  3.02it/s]
406.67607973 m 366.444808049 m 386.56044389 m
Image shape: (720, 1280, 3)
 15%|█▌        | 192/1261 [01:05<05:53,  3.02it/s]
401.856057184 m 455.07182114 m 428.463939162 m
Image shape: (720, 1280, 3)
 15%|█▌        | 193/1261 [01:05<05:55,  3.00it/s]
403.902941207 m 460.633309065 m 432.268125136 m
Image shape: (720, 1280, 3)
 15%|█▌        | 194/1261 [01:06<05:56,  2.99it/s]
418.969803707 m 345.504018032 m 382.236910869 m
Image shape: (720, 1280, 3)
 15%|█▌        | 195/1261 [01:06<05:55,  3.00it/s]
419.318519733 m 316.198662231 m 367.758590982 m
Image shape: (720, 1280, 3)
 16%|█▌        | 196/1261 [01:06<05:53,  3.02it/s]
449.342459595 m 385.156559015 m 417.249509305 m
Image shape: (720, 1280, 3)
 16%|█▌        | 197/1261 [01:07<05:51,  3.02it/s]
490.712082942 m 513.377983055 m 502.045032999 m
Image shape: (720, 1280, 3)
 16%|█▌        | 198/1261 [01:07<05:50,  3.03it/s]
532.614526112 m 1367.6026588 m 950.108592457 m
Image shape: (720, 1280, 3)
 16%|█▌        | 199/1261 [01:07<05:49,  3.04it/s]
555.944559677 m 1390.9767652 m 973.460662437 m
Image shape: (720, 1280, 3)
 16%|█▌        | 200/1261 [01:08<05:48,  3.04it/s]
565.004570859 m 1746.33476277 m 1155.66966681 m
Image shape: (720, 1280, 3)
 16%|█▌        | 201/1261 [01:08<05:49,  3.03it/s]
602.813160414 m 543.745462248 m 573.279311331 m
Image shape: (720, 1280, 3)
 16%|█▌        | 202/1261 [01:08<05:50,  3.02it/s]
612.52918723 m 445.703896874 m 529.116542052 m
Image shape: (720, 1280, 3)
 16%|█▌        | 203/1261 [01:09<05:51,  3.01it/s]
637.833709894 m 367.531643021 m 502.682676458 m
Image shape: (720, 1280, 3)
 16%|█▌        | 204/1261 [01:09<05:50,  3.02it/s]
651.181434078 m 454.244798073 m 552.713116076 m
Image shape: (720, 1280, 3)
 16%|█▋        | 205/1261 [01:09<05:53,  2.99it/s]
625.70853424 m 596.22714812 m 610.96784118 m
Image shape: (720, 1280, 3)
 16%|█▋        | 206/1261 [01:10<05:54,  2.98it/s]
599.585002567 m 579.413551183 m 589.499276875 m
Image shape: (720, 1280, 3)
 16%|█▋        | 207/1261 [01:10<05:52,  2.99it/s]
555.709693216 m 432.232693516 m 493.971193366 m
Image shape: (720, 1280, 3)
 16%|█▋        | 208/1261 [01:10<05:51,  2.99it/s]
522.924033336 m 297.463055243 m 410.193544289 m
Image shape: (720, 1280, 3)
 17%|█▋        | 209/1261 [01:11<05:50,  3.00it/s]
564.791774921 m 380.852437772 m 472.822106346 m
Image shape: (720, 1280, 3)
 17%|█▋        | 210/1261 [01:11<05:48,  3.01it/s]
571.282956265 m 474.274426994 m 522.77869163 m
Image shape: (720, 1280, 3)
 17%|█▋        | 211/1261 [01:11<05:49,  3.00it/s]
543.928323321 m 706.628608818 m 625.278466069 m
Image shape: (720, 1280, 3)
 17%|█▋        | 212/1261 [01:12<05:48,  3.01it/s]
554.052403497 m 815.453266603 m 684.75283505 m
Image shape: (720, 1280, 3)
 17%|█▋        | 213/1261 [01:12<05:49,  3.00it/s]
516.297928028 m 396.600167459 m 456.449047743 m
Image shape: (720, 1280, 3)
 17%|█▋        | 214/1261 [01:12<05:54,  2.95it/s]
506.252962901 m 306.430923556 m 406.341943228 m
Image shape: (720, 1280, 3)
 17%|█▋        | 215/1261 [01:13<06:14,  2.80it/s]
494.457760229 m 309.73660163 m 402.097180929 m
Image shape: (720, 1280, 3)
 17%|█▋        | 216/1261 [01:13<06:11,  2.82it/s]
481.606791684 m 635.206585102 m 558.406688393 m
Image shape: (720, 1280, 3)
 17%|█▋        | 217/1261 [01:13<06:02,  2.88it/s]
473.39230964 m 685.666261293 m 579.529285467 m
Image shape: (720, 1280, 3)
 17%|█▋        | 218/1261 [01:14<05:58,  2.91it/s]
517.410596675 m 817.363148196 m 667.386872436 m
Image shape: (720, 1280, 3)
 17%|█▋        | 219/1261 [01:14<05:55,  2.93it/s]
493.791746909 m 567.225163049 m 530.508454979 m
Image shape: (720, 1280, 3)
 17%|█▋        | 220/1261 [01:14<05:52,  2.95it/s]
556.265010948 m 459.41409984 m 507.839555394 m
Image shape: (720, 1280, 3)
 18%|█▊        | 221/1261 [01:15<05:51,  2.96it/s]
559.919195719 m 454.112388977 m 507.015792348 m
Image shape: (720, 1280, 3)
 18%|█▊        | 222/1261 [01:15<05:48,  2.98it/s]
577.879133114 m 552.057839598 m 564.968486356 m
Image shape: (720, 1280, 3)
 18%|█▊        | 223/1261 [01:15<05:49,  2.97it/s]
603.959473768 m 500.080387955 m 552.019930861 m
Image shape: (720, 1280, 3)
 18%|█▊        | 224/1261 [01:16<05:47,  2.98it/s]
602.009860479 m 571.785308129 m 586.897584304 m
Image shape: (720, 1280, 3)
 18%|█▊        | 225/1261 [01:16<05:49,  2.97it/s]
588.068149393 m 433.822394258 m 510.945271825 m
Image shape: (720, 1280, 3)
 18%|█▊        | 226/1261 [01:16<05:49,  2.96it/s]
574.984945432 m 405.793988723 m 490.389467078 m
Image shape: (720, 1280, 3)
 18%|█▊        | 227/1261 [01:17<05:49,  2.96it/s]
611.871261599 m 574.540675847 m 593.205968723 m
Image shape: (720, 1280, 3)
 18%|█▊        | 228/1261 [01:17<05:47,  2.98it/s]
651.069394284 m 567.101763838 m 609.085579061 m
Image shape: (720, 1280, 3)
 18%|█▊        | 229/1261 [01:17<05:48,  2.96it/s]
655.843296356 m 924.427381949 m 790.135339152 m
Image shape: (720, 1280, 3)
 18%|█▊        | 230/1261 [01:18<05:47,  2.97it/s]
732.175594238 m 892.405068512 m 812.290331375 m
Image shape: (720, 1280, 3)
 18%|█▊        | 231/1261 [01:18<05:46,  2.97it/s]
725.705447848 m 688.812201063 m 707.258824455 m
Image shape: (720, 1280, 3)
 18%|█▊        | 232/1261 [01:18<05:45,  2.98it/s]
762.2574815 m 607.989295281 m 685.123388391 m
Image shape: (720, 1280, 3)
 18%|█▊        | 233/1261 [01:19<05:52,  2.92it/s]
848.968274805 m 530.487587949 m 689.727931377 m
Image shape: (720, 1280, 3)
 19%|█▊        | 234/1261 [01:19<05:48,  2.95it/s]
890.408831435 m 541.501682673 m 715.955257054 m
Image shape: (720, 1280, 3)
 19%|█▊        | 235/1261 [01:19<05:46,  2.96it/s]
883.694120016 m 541.328997465 m 712.51155874 m
Image shape: (720, 1280, 3)
 19%|█▊        | 236/1261 [01:20<05:44,  2.98it/s]
811.963575636 m 497.98421344 m 654.973894538 m
Image shape: (720, 1280, 3)
 19%|█▉        | 237/1261 [01:20<05:42,  2.99it/s]
703.182869268 m 328.020491711 m 515.60168049 m
Image shape: (720, 1280, 3)
 19%|█▉        | 238/1261 [01:20<05:41,  2.99it/s]
715.360692775 m 295.007364038 m 505.184028407 m
Image shape: (720, 1280, 3)
 19%|█▉        | 239/1261 [01:21<05:40,  3.00it/s]
675.339705037 m 291.784486352 m 483.562095694 m
Image shape: (720, 1280, 3)
 19%|█▉        | 240/1261 [01:21<05:39,  3.01it/s]
690.463900532 m 303.282706861 m 496.873303696 m
Image shape: (720, 1280, 3)
 19%|█▉        | 241/1261 [01:21<05:38,  3.02it/s]
654.988779926 m 336.545471632 m 495.767125779 m
Image shape: (720, 1280, 3)
 19%|█▉        | 242/1261 [01:22<05:39,  3.00it/s]
636.467432832 m 500.607978292 m 568.537705562 m
Image shape: (720, 1280, 3)
 19%|█▉        | 243/1261 [01:22<05:38,  3.01it/s]
596.634635712 m 431.439408317 m 514.037022014 m
Image shape: (720, 1280, 3)
 19%|█▉        | 244/1261 [01:22<05:39,  3.00it/s]
606.081799124 m 413.673013267 m 509.877406195 m
Image shape: (720, 1280, 3)
 19%|█▉        | 245/1261 [01:23<05:38,  3.00it/s]
594.131199928 m 363.271445016 m 478.701322472 m
Image shape: (720, 1280, 3)
 20%|█▉        | 246/1261 [01:23<05:39,  2.99it/s]
569.711856683 m 367.510709438 m 468.61128306 m
Image shape: (720, 1280, 3)
 20%|█▉        | 247/1261 [01:23<05:38,  2.99it/s]
600.269211112 m 452.102096693 m 526.185653902 m
Image shape: (720, 1280, 3)
 20%|█▉        | 248/1261 [01:24<05:39,  2.99it/s]
591.160670666 m 282.641582147 m 436.901126406 m
Image shape: (720, 1280, 3)
 20%|█▉        | 249/1261 [01:24<05:37,  3.00it/s]
577.782527924 m 273.501588395 m 425.642058159 m
Image shape: (720, 1280, 3)
 20%|█▉        | 250/1261 [01:24<05:38,  2.98it/s]
584.909650786 m 280.743672046 m 432.826661416 m
Image shape: (720, 1280, 3)
 20%|█▉        | 251/1261 [01:25<05:38,  2.98it/s]
601.169674526 m 299.47113652 m 450.320405523 m
Image shape: (720, 1280, 3)
 20%|█▉        | 252/1261 [01:25<05:39,  2.97it/s]
669.781846156 m 293.362371664 m 481.57210891 m
Image shape: (720, 1280, 3)
 20%|██        | 253/1261 [01:25<05:38,  2.98it/s]
703.805150977 m 328.708573794 m 516.256862386 m
Image shape: (720, 1280, 3)
 20%|██        | 254/1261 [01:26<05:38,  2.98it/s]
644.748518834 m 510.801889221 m 577.775204028 m
Image shape: (720, 1280, 3)
 20%|██        | 255/1261 [01:26<05:36,  2.99it/s]
648.406766272 m 487.436707506 m 567.921736889 m
Image shape: (720, 1280, 3)
 20%|██        | 256/1261 [01:26<05:35,  2.99it/s]
620.952709153 m 492.830109361 m 556.891409257 m
Image shape: (720, 1280, 3)
 20%|██        | 257/1261 [01:27<05:35,  2.99it/s]
609.199760514 m 426.675937824 m 517.937849169 m
Image shape: (720, 1280, 3)
 20%|██        | 258/1261 [01:27<05:35,  2.99it/s]
651.258653487 m 513.655293099 m 582.456973293 m
Image shape: (720, 1280, 3)
 21%|██        | 259/1261 [01:27<05:35,  2.99it/s]
620.867743946 m 528.168558129 m 574.518151037 m
Image shape: (720, 1280, 3)
 21%|██        | 260/1261 [01:28<05:35,  2.98it/s]
615.130304146 m 400.167963871 m 507.649134009 m
Image shape: (720, 1280, 3)
 21%|██        | 261/1261 [01:28<05:34,  2.99it/s]
708.913656883 m 399.749549956 m 554.33160342 m
Image shape: (720, 1280, 3)
 21%|██        | 262/1261 [01:28<05:32,  3.01it/s]
682.617068365 m 408.177135205 m 545.397101785 m
Image shape: (720, 1280, 3)
 21%|██        | 263/1261 [01:29<05:32,  3.00it/s]
747.330786306 m 408.613901032 m 577.972343669 m
Image shape: (720, 1280, 3)
 21%|██        | 264/1261 [01:29<05:32,  3.00it/s]
813.045444265 m 436.735890733 m 624.890667499 m
Image shape: (720, 1280, 3)
 21%|██        | 265/1261 [01:29<05:32,  2.99it/s]
754.020072322 m 440.194080095 m 597.107076209 m
Image shape: (720, 1280, 3)
 21%|██        | 266/1261 [01:30<05:33,  2.98it/s]
828.089449926 m 547.980878843 m 688.035164384 m
Image shape: (720, 1280, 3)
 21%|██        | 267/1261 [01:30<05:33,  2.98it/s]
752.844064434 m 570.942420656 m 661.893242545 m
Image shape: (720, 1280, 3)
 21%|██▏       | 268/1261 [01:30<05:31,  2.99it/s]
834.985224206 m 549.029256855 m 692.007240531 m
Image shape: (720, 1280, 3)
 21%|██▏       | 269/1261 [01:31<05:31,  2.99it/s]
776.812116003 m 708.501770097 m 742.65694305 m
Image shape: (720, 1280, 3)
 21%|██▏       | 270/1261 [01:31<05:33,  2.97it/s]
791.026998769 m 526.027220536 m 658.527109653 m
Image shape: (720, 1280, 3)
 21%|██▏       | 271/1261 [01:31<05:34,  2.96it/s]
778.461303202 m 546.149856672 m 662.305579937 m
Image shape: (720, 1280, 3)
 22%|██▏       | 272/1261 [01:32<05:33,  2.97it/s]
716.920656678 m 465.536259073 m 591.228457876 m
Image shape: (720, 1280, 3)
 22%|██▏       | 273/1261 [01:32<05:32,  2.97it/s]
690.717118429 m 468.611703858 m 579.664411143 m
Image shape: (720, 1280, 3)
 22%|██▏       | 274/1261 [01:32<05:30,  2.99it/s]
635.215113792 m 522.138975599 m 578.677044696 m
Image shape: (720, 1280, 3)
 22%|██▏       | 275/1261 [01:33<05:30,  2.98it/s]
664.198761452 m 562.891658175 m 613.545209814 m
Image shape: (720, 1280, 3)
 22%|██▏       | 276/1261 [01:33<05:31,  2.97it/s]
739.692960715 m 742.849877219 m 741.271418967 m
Image shape: (720, 1280, 3)
 22%|██▏       | 277/1261 [01:33<05:31,  2.97it/s]
778.246760918 m 661.984993264 m 720.115877091 m
Image shape: (720, 1280, 3)
 22%|██▏       | 278/1261 [01:34<05:29,  2.98it/s]
802.23160175 m 728.90365581 m 765.56762878 m
Image shape: (720, 1280, 3)
 22%|██▏       | 279/1261 [01:34<05:27,  3.00it/s]
756.554974598 m 640.826688092 m 698.690831345 m
Image shape: (720, 1280, 3)
 22%|██▏       | 280/1261 [01:34<05:25,  3.01it/s]
811.940263679 m 624.108477181 m 718.02437043 m
Image shape: (720, 1280, 3)
 22%|██▏       | 281/1261 [01:35<05:24,  3.02it/s]
812.461164484 m 548.237664713 m 680.349414599 m
Image shape: (720, 1280, 3)
 22%|██▏       | 282/1261 [01:35<05:24,  3.02it/s]
796.218638091 m 535.58827582 m 665.903456956 m
Image shape: (720, 1280, 3)
 22%|██▏       | 283/1261 [01:35<05:22,  3.03it/s]
859.564290534 m 577.786270149 m 718.675280341 m
Image shape: (720, 1280, 3)
 23%|██▎       | 284/1261 [01:36<05:24,  3.01it/s]
993.402978901 m 564.345376272 m 778.874177586 m
Image shape: (720, 1280, 3)
 23%|██▎       | 285/1261 [01:36<05:23,  3.01it/s]
962.1613222 m 661.884326603 m 812.022824402 m
Image shape: (720, 1280, 3)
 23%|██▎       | 286/1261 [01:36<05:25,  3.00it/s]
893.964932679 m 13664.8447949 m 7279.40486379 m
Image shape: (720, 1280, 3)
 23%|██▎       | 287/1261 [01:37<05:26,  2.99it/s]
921.737541528 m 61703.7488661 m 31312.7432038 m
Image shape: (720, 1280, 3)
 23%|██▎       | 288/1261 [01:37<05:25,  2.99it/s]
1154.87792122 m 3552.59262769 m 2353.73527445 m
Image shape: (720, 1280, 3)
 23%|██▎       | 289/1261 [01:37<05:25,  2.98it/s]
1235.91113915 m 564.876387743 m 900.393763445 m
Image shape: (720, 1280, 3)
 23%|██▎       | 290/1261 [01:38<05:26,  2.98it/s]
1229.57571395 m 1198.95530869 m 1214.26551132 m
Image shape: (720, 1280, 3)
 23%|██▎       | 291/1261 [01:38<05:32,  2.92it/s]
1348.55155942 m 863.164231293 m 1105.85789536 m
Image shape: (720, 1280, 3)
 23%|██▎       | 292/1261 [01:38<05:37,  2.87it/s]
1072.70388265 m 835.327633879 m 954.015758264 m
Image shape: (720, 1280, 3)
 23%|██▎       | 293/1261 [01:39<05:41,  2.84it/s]
1042.47423373 m 1572.15852099 m 1307.31637736 m
Image shape: (720, 1280, 3)
 23%|██▎       | 294/1261 [01:39<05:36,  2.88it/s]
1030.62720856 m 719.317557062 m 874.972382812 m
Image shape: (720, 1280, 3)
 23%|██▎       | 295/1261 [01:39<05:32,  2.91it/s]
1024.21107411 m 708.526547687 m 866.3688109 m
Image shape: (720, 1280, 3)
 23%|██▎       | 296/1261 [01:40<05:30,  2.92it/s]
1182.98905081 m 685.363945003 m 934.176497907 m
Image shape: (720, 1280, 3)
 24%|██▎       | 297/1261 [01:40<05:26,  2.95it/s]
1264.69808314 m 753.159250347 m 1008.92866674 m
Image shape: (720, 1280, 3)
 24%|██▎       | 298/1261 [01:40<05:26,  2.95it/s]
1273.06593858 m 36150.8682419 m 18711.9670903 m
Image shape: (720, 1280, 3)
 24%|██▎       | 299/1261 [01:41<05:23,  2.97it/s]
1384.61817371 m 3965.72826322 m 2675.17321847 m
Image shape: (720, 1280, 3)
 24%|██▍       | 300/1261 [01:41<05:21,  2.99it/s]
1452.31786979 m 4319.33328555 m 2885.82557767 m
Image shape: (720, 1280, 3)
 24%|██▍       | 301/1261 [01:41<05:19,  3.00it/s]
1538.47283754 m 1092.59571577 m 1315.53427666 m
Image shape: (720, 1280, 3)
 24%|██▍       | 302/1261 [01:42<05:20,  2.99it/s]
1307.31959682 m 1504.95258687 m 1406.13609184 m
Image shape: (720, 1280, 3)
 24%|██▍       | 303/1261 [01:42<05:20,  2.99it/s]
2048.41716718 m 1025.40743486 m 1536.91230102 m
Image shape: (720, 1280, 3)
 24%|██▍       | 304/1261 [01:42<05:20,  2.99it/s]
1477.45296 m 924.009162423 m 1200.73106121 m
Image shape: (720, 1280, 3)
 24%|██▍       | 305/1261 [01:43<05:18,  3.00it/s]
1818.11545429 m 883.095247484 m 1350.60535089 m
Image shape: (720, 1280, 3)
 24%|██▍       | 306/1261 [01:43<05:19,  2.98it/s]
1721.98600595 m 771.547929091 m 1246.76696752 m
Image shape: (720, 1280, 3)
 24%|██▍       | 307/1261 [01:43<05:19,  2.99it/s]
2202.11432393 m 934.4337511 m 1568.27403752 m
Image shape: (720, 1280, 3)
 24%|██▍       | 308/1261 [01:44<05:19,  2.98it/s]
1620.65173158 m 580.871225146 m 1100.76147836 m
Image shape: (720, 1280, 3)
 25%|██▍       | 309/1261 [01:44<05:18,  2.99it/s]
1995.71421371 m 856.849460856 m 1426.28183728 m
Image shape: (720, 1280, 3)
 25%|██▍       | 310/1261 [01:44<05:17,  3.00it/s]
2368.21929601 m 3938.19023415 m 3153.20476508 m
Image shape: (720, 1280, 3)
 25%|██▍       | 311/1261 [01:45<05:15,  3.01it/s]
2913.66205821 m 970.950144456 m 1942.30610133 m
Image shape: (720, 1280, 3)
 25%|██▍       | 312/1261 [01:45<05:15,  3.00it/s]
3144.59035086 m 1010.9855958 m 2077.78797333 m
Image shape: (720, 1280, 3)
 25%|██▍       | 313/1261 [01:45<05:15,  3.00it/s]
3748.63926643 m 2817.75674671 m 3283.19800657 m
Image shape: (720, 1280, 3)
 25%|██▍       | 314/1261 [01:46<05:17,  2.99it/s]
8389.33207773 m 2854.38563156 m 5621.85885464 m
Image shape: (720, 1280, 3)
 25%|██▍       | 315/1261 [01:46<05:16,  2.99it/s]
60106.8703054 m 3815.80947464 m 31961.33989 m
Image shape: (720, 1280, 3)
 25%|██▌       | 316/1261 [01:47<05:15,  3.00it/s]
15247.4578797 m 3319.91897206 m 9283.6884259 m
Image shape: (720, 1280, 3)
 25%|██▌       | 317/1261 [01:47<05:15,  3.00it/s]
226614.792104 m 1552.36681177 m 114083.579458 m
Image shape: (720, 1280, 3)
 25%|██▌       | 318/1261 [01:47<05:13,  3.01it/s]
9031.69638335 m 936.170777542 m 4983.93358045 m
Image shape: (720, 1280, 3)
 25%|██▌       | 319/1261 [01:47<05:13,  3.01it/s]
9203.9539736 m 1103.36001047 m 5153.65699203 m
Image shape: (720, 1280, 3)
 25%|██▌       | 320/1261 [01:48<05:13,  3.00it/s]
3393.45793211 m 1034.7824002 m 2214.12016616 m
Image shape: (720, 1280, 3)
 25%|██▌       | 321/1261 [01:48<05:13,  3.00it/s]
3962.09935201 m 1181.30266664 m 2571.70100933 m
Image shape: (720, 1280, 3)
 26%|██▌       | 322/1261 [01:49<05:15,  2.98it/s]
14038.7339459 m 2018.25097707 m 8028.49246149 m
Image shape: (720, 1280, 3)
 26%|██▌       | 323/1261 [01:49<05:14,  2.98it/s]
39805.4203476 m 8191.66318306 m 23998.5417653 m
Image shape: (720, 1280, 3)
 26%|██▌       | 324/1261 [01:49<05:14,  2.98it/s]
4111.12653625 m 11613.058672 m 7862.09260411 m
Image shape: (720, 1280, 3)
 26%|██▌       | 325/1261 [01:50<05:15,  2.97it/s]
5778.3629222 m 29750.0803357 m 17764.221629 m
Image shape: (720, 1280, 3)
 26%|██▌       | 326/1261 [01:50<05:14,  2.97it/s]
13988.2207851 m 2078.32452179 m 8033.27265347 m
Image shape: (720, 1280, 3)
 26%|██▌       | 327/1261 [01:50<05:14,  2.97it/s]
11859.3721231 m 2454.95724794 m 7157.16468553 m
Image shape: (720, 1280, 3)
 26%|██▌       | 328/1261 [01:51<05:14,  2.97it/s]
2849.94589845 m 1357.33754038 m 2103.64171942 m
Image shape: (720, 1280, 3)
 26%|██▌       | 329/1261 [01:51<05:11,  2.99it/s]
14993.4116501 m 4316.24123942 m 9654.82644474 m
Image shape: (720, 1280, 3)
 26%|██▌       | 330/1261 [01:51<05:11,  2.99it/s]
3659.96398924 m 1302.01482688 m 2480.98940806 m
Image shape: (720, 1280, 3)
 26%|██▌       | 331/1261 [01:52<05:14,  2.96it/s]
54325.2397566 m 6541.79262205 m 30433.5161893 m
Image shape: (720, 1280, 3)
 26%|██▋       | 332/1261 [01:52<05:12,  2.97it/s]
6854.17589961 m 1477.11108649 m 4165.64349305 m
Image shape: (720, 1280, 3)
 26%|██▋       | 333/1261 [01:52<05:14,  2.95it/s]
10467.8910546 m 994.329034717 m 5731.11004468 m
Image shape: (720, 1280, 3)
 26%|██▋       | 334/1261 [01:53<05:12,  2.97it/s]
7801.21803724 m 6467.06665856 m 7134.1423479 m
Image shape: (720, 1280, 3)
 27%|██▋       | 335/1261 [01:53<05:13,  2.96it/s]
5119.98342146 m 2397.82924839 m 3758.90633492 m
Image shape: (720, 1280, 3)
 27%|██▋       | 336/1261 [01:53<05:11,  2.97it/s]
3468.08021185 m 30920.4371397 m 17194.2586758 m
Image shape: (720, 1280, 3)
 27%|██▋       | 337/1261 [01:54<05:11,  2.97it/s]
5201.49811948 m 8649.92599347 m 6925.71205648 m
Image shape: (720, 1280, 3)
 27%|██▋       | 338/1261 [01:54<05:12,  2.96it/s]
3145.46063513 m 7378.14095917 m 5261.80079715 m
Image shape: (720, 1280, 3)
 27%|██▋       | 339/1261 [01:54<05:11,  2.96it/s]
4443.35027526 m 2423.48072121 m 3433.41549824 m
Image shape: (720, 1280, 3)
 27%|██▋       | 340/1261 [01:55<05:09,  2.97it/s]
3044.41706923 m 1807.54914229 m 2425.98310576 m
Image shape: (720, 1280, 3)
 27%|██▋       | 341/1261 [01:55<05:08,  2.98it/s]
2580.25412083 m 1923.2710629 m 2251.76259186 m
Image shape: (720, 1280, 3)
 27%|██▋       | 342/1261 [01:55<05:07,  2.99it/s]
3272.91526201 m 851.867885963 m 2062.39157398 m
Image shape: (720, 1280, 3)
 27%|██▋       | 343/1261 [01:56<05:07,  2.98it/s]
2342.5550913 m 905.986053296 m 1624.2705723 m
Image shape: (720, 1280, 3)
 27%|██▋       | 344/1261 [01:56<05:06,  2.99it/s]
2077.89564466 m 1011.2151309 m 1544.55538778 m
Image shape: (720, 1280, 3)
 27%|██▋       | 345/1261 [01:56<05:08,  2.97it/s]
4315.89460826 m 5296.02744062 m 4805.96102444 m
Image shape: (720, 1280, 3)
 27%|██▋       | 346/1261 [01:57<05:08,  2.97it/s]
13145.5789195 m 2018.81999566 m 7582.19945757 m
Image shape: (720, 1280, 3)
 28%|██▊       | 347/1261 [01:57<05:09,  2.95it/s]
3780.89793216 m 6220.10726752 m 5000.50259984 m
Image shape: (720, 1280, 3)
 28%|██▊       | 348/1261 [01:57<05:08,  2.96it/s]
14176.8671769 m 4697.55575569 m 9437.21146629 m
Image shape: (720, 1280, 3)
 28%|██▊       | 349/1261 [01:58<05:08,  2.95it/s]
6700.80857053 m 4849.28436575 m 5775.04646814 m
Image shape: (720, 1280, 3)
 28%|██▊       | 350/1261 [01:58<05:07,  2.96it/s]
5550.20873901 m 8223.71567649 m 6886.96220775 m
Image shape: (720, 1280, 3)
 28%|██▊       | 351/1261 [01:58<05:06,  2.97it/s]
43916.1860088 m 6001.86106568 m 24959.0235372 m
Image shape: (720, 1280, 3)
 28%|██▊       | 352/1261 [01:59<05:05,  2.97it/s]
9095.70500185 m 4391.27919676 m 6743.49209931 m
Image shape: (720, 1280, 3)
 28%|██▊       | 353/1261 [01:59<05:04,  2.98it/s]
5344.34528381 m 7077.37375693 m 6210.85952037 m
Image shape: (720, 1280, 3)
 28%|██▊       | 354/1261 [01:59<05:04,  2.98it/s]
3210.46226298 m 1778.16716523 m 2494.31471411 m
Image shape: (720, 1280, 3)
 28%|██▊       | 355/1261 [02:00<05:05,  2.97it/s]
3301.46688836 m 1536.24389226 m 2418.85539031 m
Image shape: (720, 1280, 3)
 28%|██▊       | 356/1261 [02:00<05:06,  2.96it/s]
2991.30936668 m 1385.10689718 m 2188.20813193 m
Image shape: (720, 1280, 3)
 28%|██▊       | 357/1261 [02:00<05:06,  2.95it/s]
4519.48497736 m 3021.11686626 m 3770.30092181 m
Image shape: (720, 1280, 3)
 28%|██▊       | 358/1261 [02:01<05:05,  2.96it/s]
4211.79604224 m 1330.61869794 m 2771.20737009 m
Image shape: (720, 1280, 3)
 28%|██▊       | 359/1261 [02:01<05:04,  2.96it/s]
41741.8173909 m 3507.74005555 m 22624.7787232 m
Image shape: (720, 1280, 3)
 29%|██▊       | 360/1261 [02:01<05:02,  2.98it/s]
8112.09768709 m 3233.35633008 m 5672.72700859 m
Image shape: (720, 1280, 3)
 29%|██▊       | 361/1261 [02:02<05:01,  2.98it/s]
7652.54492117 m 3951.18777888 m 5801.86635003 m
Image shape: (720, 1280, 3)
 29%|██▊       | 362/1261 [02:02<05:00,  2.99it/s]
2340.15903249 m 3810.5937998 m 3075.37641614 m
Image shape: (720, 1280, 3)
 29%|██▉       | 363/1261 [02:02<05:02,  2.97it/s]
1576.64710505 m 3991.59254677 m 2784.11982591 m
Image shape: (720, 1280, 3)
 29%|██▉       | 364/1261 [02:03<05:02,  2.97it/s]
1419.41900369 m 5365.423117 m 3392.42106035 m
Image shape: (720, 1280, 3)
 29%|██▉       | 365/1261 [02:03<05:02,  2.96it/s]
1163.69996236 m 2933.54222703 m 2048.6210947 m
Image shape: (720, 1280, 3)
 29%|██▉       | 366/1261 [02:03<05:02,  2.96it/s]
960.453506458 m 4379.62059193 m 2670.03704919 m
Image shape: (720, 1280, 3)
 29%|██▉       | 367/1261 [02:04<05:01,  2.97it/s]
1305.31846207 m 4531.48466717 m 2918.40156462 m
Image shape: (720, 1280, 3)
 29%|██▉       | 368/1261 [02:04<05:07,  2.90it/s]
1243.21314991 m 1292.26973171 m 1267.74144081 m
Image shape: (720, 1280, 3)
 29%|██▉       | 369/1261 [02:04<05:15,  2.83it/s]
894.716321721 m 5035.97544075 m 2965.34588124 m
Image shape: (720, 1280, 3)
 29%|██▉       | 370/1261 [02:05<05:16,  2.82it/s]
959.013060905 m 2340.41337286 m 1649.71321688 m
Image shape: (720, 1280, 3)
 29%|██▉       | 371/1261 [02:05<05:10,  2.87it/s]
1132.40784362 m 6972.70601252 m 4052.55692807 m
Image shape: (720, 1280, 3)
 30%|██▉       | 372/1261 [02:05<05:06,  2.90it/s]
1157.18664048 m 1967.68463026 m 1562.43563537 m
Image shape: (720, 1280, 3)
 30%|██▉       | 373/1261 [02:06<05:03,  2.92it/s]
1484.64606931 m 1907.38042169 m 1696.0132455 m
Image shape: (720, 1280, 3)
 30%|██▉       | 374/1261 [02:06<05:02,  2.94it/s]
1441.7462738 m 34070.4057426 m 17756.0760082 m
Image shape: (720, 1280, 3)
 30%|██▉       | 375/1261 [02:06<05:00,  2.94it/s]
1874.98749156 m 11434.1800476 m 6654.5837696 m
Image shape: (720, 1280, 3)
 30%|██▉       | 376/1261 [02:07<04:58,  2.96it/s]
5548.27204511 m 1410.21848197 m 3479.24526354 m
Image shape: (720, 1280, 3)
 30%|██▉       | 377/1261 [02:07<04:57,  2.97it/s]
7094.12603646 m 1249.39222137 m 4171.75912892 m
Image shape: (720, 1280, 3)
 30%|██▉       | 378/1261 [02:07<04:56,  2.98it/s]
13778.7558575 m 1269.29376251 m 7524.02481 m
Image shape: (720, 1280, 3)
 30%|███       | 379/1261 [02:08<04:56,  2.98it/s]
4497.42518883 m 1236.92573678 m 2867.17546281 m
Image shape: (720, 1280, 3)
 30%|███       | 380/1261 [02:08<04:56,  2.97it/s]
2812.77835649 m 1132.95558967 m 1972.86697308 m
Image shape: (720, 1280, 3)
 30%|███       | 381/1261 [02:08<04:57,  2.96it/s]
5708.17368324 m 2793.26750933 m 4250.72059629 m
Image shape: (720, 1280, 3)
 30%|███       | 382/1261 [02:09<04:55,  2.98it/s]
5251.32261838 m 1585.05762706 m 3418.19012272 m
Image shape: (720, 1280, 3)
 30%|███       | 383/1261 [02:09<04:54,  2.99it/s]
4259.67246461 m 2539.83966052 m 3399.75606256 m
Image shape: (720, 1280, 3)
 30%|███       | 384/1261 [02:09<04:52,  3.00it/s]
4987.32598893 m 2224.58341421 m 3605.95470157 m
Image shape: (720, 1280, 3)
 31%|███       | 385/1261 [02:10<04:51,  3.00it/s]
9004.06692015 m 2226.08759346 m 5615.07725681 m
Image shape: (720, 1280, 3)
 31%|███       | 386/1261 [02:10<04:50,  3.01it/s]
32248.4506077 m 3667.46818296 m 17957.9593953 m
Image shape: (720, 1280, 3)
 31%|███       | 387/1261 [02:10<04:50,  3.01it/s]
22657.4415558 m 6739.62728886 m 14698.5344223 m
Image shape: (720, 1280, 3)
 31%|███       | 388/1261 [02:11<04:50,  3.01it/s]
11090.4155637 m 5136.53611436 m 8113.47583905 m
Image shape: (720, 1280, 3)
 31%|███       | 389/1261 [02:11<04:50,  3.00it/s]
73065.5601483 m 6287.64508229 m 39676.6026153 m
Image shape: (720, 1280, 3)
 31%|███       | 390/1261 [02:11<04:50,  3.00it/s]
6980.52154382 m 1804.36842065 m 4392.44498224 m
Image shape: (720, 1280, 3)
 31%|███       | 391/1261 [02:12<04:50,  2.99it/s]
136965.715332 m 1697.98834482 m 69331.8518382 m
Image shape: (720, 1280, 3)
 31%|███       | 392/1261 [02:12<04:50,  2.99it/s]
43039.6658895 m 1998.29782254 m 22518.981856 m
Image shape: (720, 1280, 3)
 31%|███       | 393/1261 [02:12<04:49,  3.00it/s]
10073.1175613 m 4193.74393217 m 7133.43074676 m
Image shape: (720, 1280, 3)
 31%|███       | 394/1261 [02:13<04:50,  2.99it/s]
2540.55569992 m 1996.87659262 m 2268.71614627 m
Image shape: (720, 1280, 3)
 31%|███▏      | 395/1261 [02:13<04:50,  2.98it/s]
2145.05527883 m 133154.568099 m 67649.8116887 m
Image shape: (720, 1280, 3)
 31%|███▏      | 396/1261 [02:13<04:49,  2.99it/s]
2148.87448918 m 16389.2418963 m 9269.05819277 m
Image shape: (720, 1280, 3)
 31%|███▏      | 397/1261 [02:14<04:48,  3.00it/s]
2000.90219985 m 2436.86757796 m 2218.88488891 m
Image shape: (720, 1280, 3)
 32%|███▏      | 398/1261 [02:14<04:48,  2.99it/s]
1866.3439446 m 2048.10775238 m 1957.22584849 m
Image shape: (720, 1280, 3)
 32%|███▏      | 399/1261 [02:14<04:48,  2.99it/s]
2046.57036852 m 2349.08052607 m 2197.82544729 m
Image shape: (720, 1280, 3)
 32%|███▏      | 400/1261 [02:15<04:49,  2.98it/s]
2045.29259431 m 3322.06255204 m 2683.67757317 m
Image shape: (720, 1280, 3)
 32%|███▏      | 401/1261 [02:15<04:50,  2.96it/s]
2103.73299418 m 87610.6841603 m 44857.2085772 m
Image shape: (720, 1280, 3)
 32%|███▏      | 402/1261 [02:15<04:49,  2.96it/s]
4248.63431482 m 1838.37699695 m 3043.50565588 m
Image shape: (720, 1280, 3)
 32%|███▏      | 403/1261 [02:16<04:47,  2.98it/s]
7355.67313476 m 1489.93958372 m 4422.80635924 m
Image shape: (720, 1280, 3)
 32%|███▏      | 404/1261 [02:16<04:46,  2.99it/s]
4171.33914396 m 1815.15717515 m 2993.24815955 m
Image shape: (720, 1280, 3)
 32%|███▏      | 405/1261 [02:16<04:47,  2.98it/s]
34149.9405188 m 3813.42901537 m 18981.6847671 m
Image shape: (720, 1280, 3)
 32%|███▏      | 406/1261 [02:17<04:46,  2.98it/s]
22875.7060476 m 1039.51998816 m 11957.6130179 m
Image shape: (720, 1280, 3)
 32%|███▏      | 407/1261 [02:17<04:46,  2.98it/s]
4697.09070886 m 2016.9843465 m 3357.03752768 m
Image shape: (720, 1280, 3)
 32%|███▏      | 408/1261 [02:17<04:45,  2.99it/s]
4407.5522411 m 3980.90567526 m 4194.22895818 m
Image shape: (720, 1280, 3)
 32%|███▏      | 409/1261 [02:18<04:44,  3.00it/s]
6966.99003735 m 4087.09895626 m 5527.0444968 m
Image shape: (720, 1280, 3)
 33%|███▎      | 410/1261 [02:18<04:43,  3.00it/s]
87467.226035 m 11889.3003185 m 49678.2631767 m
Image shape: (720, 1280, 3)
 33%|███▎      | 411/1261 [02:18<04:43,  3.00it/s]
216183.827764 m 32702.2325625 m 124443.030163 m
Image shape: (720, 1280, 3)
 33%|███▎      | 412/1261 [02:19<04:48,  2.94it/s]
7263.59925146 m 12110.788207 m 9687.19372922 m
Image shape: (720, 1280, 3)
 33%|███▎      | 413/1261 [02:19<04:46,  2.96it/s]
7707.04691143 m 3725.77575188 m 5716.41133166 m
Image shape: (720, 1280, 3)
 33%|███▎      | 414/1261 [02:19<04:44,  2.98it/s]
5342.90273984 m 2940.11953985 m 4141.51113984 m
Image shape: (720, 1280, 3)
 33%|███▎      | 415/1261 [02:20<04:43,  2.98it/s]
4501.47624134 m 3772.31076444 m 4136.89350289 m
Image shape: (720, 1280, 3)
 33%|███▎      | 416/1261 [02:20<04:42,  2.99it/s]
2490.81650063 m 4838.80941714 m 3664.81295888 m
Image shape: (720, 1280, 3)
 33%|███▎      | 417/1261 [02:20<04:42,  2.99it/s]
1949.17832842 m 10069.078925 m 6009.12862673 m
Image shape: (720, 1280, 3)
 33%|███▎      | 418/1261 [02:21<04:43,  2.97it/s]
2334.77026964 m 1385.03011664 m 1859.90019314 m
Image shape: (720, 1280, 3)
 33%|███▎      | 419/1261 [02:21<04:43,  2.97it/s]
1532.03720395 m 24850.3788265 m 13191.2080153 m
Image shape: (720, 1280, 3)
 33%|███▎      | 420/1261 [02:22<04:43,  2.97it/s]
1835.68804068 m 6056.20989249 m 3945.94896659 m
Image shape: (720, 1280, 3)
 33%|███▎      | 421/1261 [02:22<04:43,  2.96it/s]
1980.3647641 m 6804.24487647 m 4392.30482028 m
Image shape: (720, 1280, 3)
 33%|███▎      | 422/1261 [02:22<04:42,  2.97it/s]
1859.89494399 m 20506.8453337 m 11183.3701388 m
Image shape: (720, 1280, 3)
 34%|███▎      | 423/1261 [02:23<04:40,  2.99it/s]
2085.19208103 m 99166.4113994 m 50625.8017402 m
Image shape: (720, 1280, 3)
 34%|███▎      | 424/1261 [02:23<04:39,  2.99it/s]
2555.81406812 m 4672.62715365 m 3614.22061089 m
Image shape: (720, 1280, 3)
 34%|███▎      | 425/1261 [02:23<04:39,  2.99it/s]
2166.77478674 m 3025.18392105 m 2595.97935389 m
Image shape: (720, 1280, 3)
 34%|███▍      | 426/1261 [02:24<04:40,  2.98it/s]
2771.55362605 m 3045.65628409 m 2908.60495507 m
Image shape: (720, 1280, 3)
 34%|███▍      | 427/1261 [02:24<04:40,  2.97it/s]
3029.63702821 m 1916.92324075 m 2473.28013448 m
Image shape: (720, 1280, 3)
 34%|███▍      | 428/1261 [02:24<04:38,  2.99it/s]
4883.54260918 m 1662.97752656 m 3273.26006787 m
Image shape: (720, 1280, 3)
 34%|███▍      | 429/1261 [02:25<04:38,  2.99it/s]
5718.8706061 m 10865.7597763 m 8292.3151912 m
Image shape: (720, 1280, 3)
 34%|███▍      | 430/1261 [02:25<04:38,  2.99it/s]
4294.30755004 m 3442.90158931 m 3868.60456967 m
Image shape: (720, 1280, 3)
 34%|███▍      | 431/1261 [02:25<04:38,  2.98it/s]
2968.69045486 m 6522.05560997 m 4745.37303241 m
Image shape: (720, 1280, 3)
 34%|███▍      | 432/1261 [02:26<04:36,  3.00it/s]
3762.06499216 m 6345.93162132 m 5053.99830674 m
Image shape: (720, 1280, 3)
 34%|███▍      | 433/1261 [02:26<04:38,  2.98it/s]
4516.97913899 m 49175.5297503 m 26846.2544446 m
Image shape: (720, 1280, 3)
 34%|███▍      | 434/1261 [02:26<04:37,  2.98it/s]
6117.88375262 m 4296.85848075 m 5207.37111669 m
Image shape: (720, 1280, 3)
 34%|███▍      | 435/1261 [02:27<04:37,  2.98it/s]
10865.0401503 m 3382.85589668 m 7123.94802351 m
Image shape: (720, 1280, 3)
 35%|███▍      | 436/1261 [02:27<04:36,  2.99it/s]
15980.0855405 m 7182.74525085 m 11581.4153956 m
Image shape: (720, 1280, 3)
 35%|███▍      | 437/1261 [02:27<04:36,  2.99it/s]
13187.8961843 m 5746.50450518 m 9467.20034473 m
Image shape: (720, 1280, 3)
 35%|███▍      | 438/1261 [02:28<04:35,  2.99it/s]
10958.3497861 m 157622.929213 m 84290.6394996 m
Image shape: (720, 1280, 3)
 35%|███▍      | 439/1261 [02:28<04:35,  2.98it/s]
5217.10163418 m 4339.91048479 m 4778.50605948 m
Image shape: (720, 1280, 3)
 35%|███▍      | 440/1261 [02:28<04:35,  2.98it/s]
3065.59631546 m 3454.253305 m 3259.92481023 m
Image shape: (720, 1280, 3)
 35%|███▍      | 441/1261 [02:29<04:35,  2.98it/s]
2681.1944402 m 2907.43535535 m 2794.31489777 m
Image shape: (720, 1280, 3)
 35%|███▌      | 442/1261 [02:29<04:35,  2.97it/s]
3549.76960604 m 6653.21036559 m 5101.48998582 m
Image shape: (720, 1280, 3)
 35%|███▌      | 443/1261 [02:29<04:34,  2.98it/s]
6102.74591638 m 7403.3611295 m 6753.05352294 m
Image shape: (720, 1280, 3)
 35%|███▌      | 444/1261 [02:30<04:33,  2.99it/s]
4406.72178867 m 3175.26795835 m 3790.99487351 m
Image shape: (720, 1280, 3)
 35%|███▌      | 445/1261 [02:30<04:40,  2.90it/s]
7839.22908868 m 4199.39480295 m 6019.31194582 m
Image shape: (720, 1280, 3)
 35%|███▌      | 446/1261 [02:30<04:45,  2.86it/s]
3044.68658107 m 11002.6283407 m 7023.65746088 m
Image shape: (720, 1280, 3)
 35%|███▌      | 447/1261 [02:31<04:45,  2.86it/s]
2507.57509292 m 4807.93737239 m 3657.75623265 m
Image shape: (720, 1280, 3)
 36%|███▌      | 448/1261 [02:31<04:40,  2.90it/s]
2695.56148565 m 2754.48262258 m 2725.02205411 m
Image shape: (720, 1280, 3)
 36%|███▌      | 449/1261 [02:31<04:38,  2.92it/s]
2232.12151331 m 3549.95197019 m 2891.03674175 m
Image shape: (720, 1280, 3)
 36%|███▌      | 450/1261 [02:32<04:35,  2.95it/s]
2149.2510645 m 3607.64728492 m 2878.44917471 m
Image shape: (720, 1280, 3)
 36%|███▌      | 451/1261 [02:32<04:32,  2.97it/s]
2702.02788199 m 14623.898669 m 8662.96327549 m
Image shape: (720, 1280, 3)
 36%|███▌      | 452/1261 [02:32<04:31,  2.98it/s]
2585.07671826 m 1376.28491946 m 1980.68081886 m
Image shape: (720, 1280, 3)
 36%|███▌      | 453/1261 [02:33<04:31,  2.98it/s]
3540.49755895 m 2582.76362442 m 3061.63059169 m
Image shape: (720, 1280, 3)
 36%|███▌      | 454/1261 [02:33<04:30,  2.98it/s]
6241.06149179 m 3714.37483051 m 4977.71816115 m
Image shape: (720, 1280, 3)
 36%|███▌      | 455/1261 [02:33<04:29,  2.99it/s]
7607.89808781 m 2859.94256264 m 5233.92032522 m
Image shape: (720, 1280, 3)
 36%|███▌      | 456/1261 [02:34<04:29,  2.99it/s]
7378.39902561 m 48993.5991597 m 28185.9990927 m
Image shape: (720, 1280, 3)
 36%|███▌      | 457/1261 [02:34<04:28,  2.99it/s]
4698.31343159 m 14889.8115141 m 9794.06247285 m
Image shape: (720, 1280, 3)
 36%|███▋      | 458/1261 [02:34<04:28,  2.99it/s]
5836.69697634 m 8585.49643561 m 7211.09670597 m
Image shape: (720, 1280, 3)
 36%|███▋      | 459/1261 [02:35<04:27,  3.00it/s]
15274.2562067 m 3890.83881626 m 9582.5475115 m
Image shape: (720, 1280, 3)
 36%|███▋      | 460/1261 [02:35<04:29,  2.98it/s]
18395.8811273 m 5437.04950399 m 11916.4653156 m
Image shape: (720, 1280, 3)
 37%|███▋      | 461/1261 [02:35<04:30,  2.96it/s]
12271.9969818 m 2579.60953319 m 7425.80325751 m
Image shape: (720, 1280, 3)
 37%|███▋      | 462/1261 [02:36<04:30,  2.96it/s]
9215.50503404 m 2698.70618544 m 5957.10560974 m
Image shape: (720, 1280, 3)
 37%|███▋      | 463/1261 [02:36<04:28,  2.97it/s]
7146.37800171 m 3397.15111119 m 5271.76455645 m
Image shape: (720, 1280, 3)
 37%|███▋      | 464/1261 [02:36<04:26,  2.99it/s]
4912.23727721 m 10090.288656 m 7501.26296659 m
Image shape: (720, 1280, 3)
 37%|███▋      | 465/1261 [02:37<04:25,  3.00it/s]
3630.08415817 m 3592.81847178 m 3611.45131498 m
Image shape: (720, 1280, 3)
 37%|███▋      | 466/1261 [02:37<04:26,  2.98it/s]
2749.29767981 m 1067.26271219 m 1908.280196 m
Image shape: (720, 1280, 3)
 37%|███▋      | 467/1261 [02:37<04:25,  2.99it/s]
2278.44142538 m 1360.64260996 m 1819.54201767 m
Image shape: (720, 1280, 3)
 37%|███▋      | 468/1261 [02:38<04:24,  3.00it/s]
1989.39093288 m 2121.24021214 m 2055.31557251 m
Image shape: (720, 1280, 3)
 37%|███▋      | 469/1261 [02:38<04:23,  3.01it/s]
2200.27354182 m 1600.92979614 m 1900.60166898 m
Image shape: (720, 1280, 3)
 37%|███▋      | 470/1261 [02:38<04:23,  3.00it/s]
2664.60795524 m 1350.76273007 m 2007.68534265 m
Image shape: (720, 1280, 3)
 37%|███▋      | 471/1261 [02:39<04:22,  3.01it/s]
3733.74702683 m 2415.32476234 m 3074.53589458 m
Image shape: (720, 1280, 3)
 37%|███▋      | 472/1261 [02:39<04:23,  3.00it/s]
4283.72797855 m 4602.75480733 m 4443.24139294 m
Image shape: (720, 1280, 3)
 38%|███▊      | 473/1261 [02:39<04:23,  3.00it/s]
6013.62570392 m 5712.26529273 m 5862.94549833 m
Image shape: (720, 1280, 3)
 38%|███▊      | 474/1261 [02:40<04:24,  2.97it/s]
4536.00859467 m 3197.22921187 m 3866.61890327 m
Image shape: (720, 1280, 3)
 38%|███▊      | 475/1261 [02:40<04:25,  2.96it/s]
5325.04204088 m 8100.2779478 m 6712.65999434 m
Image shape: (720, 1280, 3)
 38%|███▊      | 476/1261 [02:40<04:27,  2.94it/s]
48718.2917058 m 4612.29959884 m 26665.2956523 m
Image shape: (720, 1280, 3)
 38%|███▊      | 477/1261 [02:41<04:27,  2.93it/s]
3768.75962073 m 2115.60088088 m 2942.1802508 m
Image shape: (720, 1280, 3)
 38%|███▊      | 478/1261 [02:41<04:27,  2.93it/s]
8078.81908877 m 979.394310142 m 4529.10669946 m
Image shape: (720, 1280, 3)
 38%|███▊      | 479/1261 [02:41<04:26,  2.93it/s]
21677.6307412 m 2461.99332266 m 12069.8120319 m
Image shape: (720, 1280, 3)
 38%|███▊      | 480/1261 [02:42<04:25,  2.95it/s]
28932.2606977 m 3236.28421322 m 16084.2724554 m
Image shape: (720, 1280, 3)
 38%|███▊      | 481/1261 [02:42<04:24,  2.95it/s]
11948.6577628 m 340391.838844 m 176170.248304 m
Image shape: (720, 1280, 3)
 38%|███▊      | 482/1261 [02:42<04:23,  2.95it/s]
8125.01583714 m 48794.9688349 m 28459.992336 m
Image shape: (720, 1280, 3)
 38%|███▊      | 483/1261 [02:43<04:22,  2.96it/s]
3390.10447149 m 1683.23603592 m 2536.67025371 m
Image shape: (720, 1280, 3)
 38%|███▊      | 484/1261 [02:43<04:21,  2.97it/s]
3250.32646534 m 2494.38934162 m 2872.35790348 m
Image shape: (720, 1280, 3)
 38%|███▊      | 485/1261 [02:43<04:21,  2.97it/s]
4764.46384019 m 3904.91255538 m 4334.68819779 m
Image shape: (720, 1280, 3)
 39%|███▊      | 486/1261 [02:44<04:20,  2.98it/s]
25829.9462838 m 3150.50152131 m 14490.2239026 m
Image shape: (720, 1280, 3)
 39%|███▊      | 487/1261 [02:44<04:20,  2.98it/s]
28758.6089314 m 2113.20564572 m 15435.9072886 m
Image shape: (720, 1280, 3)
 39%|███▊      | 488/1261 [02:44<04:20,  2.97it/s]
5887.73642617 m 1432.81216427 m 3660.27429522 m
Image shape: (720, 1280, 3)
 39%|███▉      | 489/1261 [02:45<04:20,  2.97it/s]
72726.3418315 m 1245.31547992 m 36985.8286557 m
Image shape: (720, 1280, 3)
 39%|███▉      | 490/1261 [02:45<04:19,  2.97it/s]
35869.9218576 m 3041.21813084 m 19455.5699942 m
Image shape: (720, 1280, 3)
 39%|███▉      | 491/1261 [02:45<04:20,  2.96it/s]
19924.3573963 m 25714.1278619 m 22819.2426291 m
Image shape: (720, 1280, 3)
 39%|███▉      | 492/1261 [02:46<04:19,  2.97it/s]
24610.6628226 m 7678.26780873 m 16144.4653157 m
Image shape: (720, 1280, 3)
 39%|███▉      | 493/1261 [02:46<04:19,  2.96it/s]
296654.732133 m 7656.98004323 m 152155.856088 m
Image shape: (720, 1280, 3)
 39%|███▉      | 494/1261 [02:46<04:17,  2.98it/s]
6188.66594513 m 6871.28012183 m 6529.97303348 m
Image shape: (720, 1280, 3)
 39%|███▉      | 495/1261 [02:47<04:17,  2.98it/s]
3631.01707915 m 5631.39750265 m 4631.2072909 m
Image shape: (720, 1280, 3)
 39%|███▉      | 496/1261 [02:47<04:16,  2.98it/s]
9135.95530532 m 27629.7657779 m 18382.8605416 m
Image shape: (720, 1280, 3)
 39%|███▉      | 497/1261 [02:47<04:17,  2.97it/s]
8961.80381276 m 1319.08117363 m 5140.4424932 m
Image shape: (720, 1280, 3)
 39%|███▉      | 498/1261 [02:48<04:16,  2.98it/s]
6093.749592 m 1652.13094743 m 3872.94026971 m
Image shape: (720, 1280, 3)
 40%|███▉      | 499/1261 [02:48<04:17,  2.96it/s]
7180.7720066 m 1478.16940686 m 4329.47070673 m
Image shape: (720, 1280, 3)
 40%|███▉      | 500/1261 [02:48<04:18,  2.94it/s]
4499.65547374 m 1982.85472126 m 3241.2550975 m
Image shape: (720, 1280, 3)
 40%|███▉      | 501/1261 [02:49<04:21,  2.90it/s]
3029.40619014 m 925.078814441 m 1977.24250229 m
Image shape: (720, 1280, 3)
 40%|███▉      | 502/1261 [02:49<04:20,  2.92it/s]
4260.86107293 m 1456.45602588 m 2858.65854941 m
Image shape: (720, 1280, 3)
 40%|███▉      | 503/1261 [02:49<04:17,  2.94it/s]
7371.51633688 m 1830.37234086 m 4600.94433887 m
Image shape: (720, 1280, 3)
 40%|███▉      | 504/1261 [02:50<04:17,  2.94it/s]
3404.32792342 m 5573.60094906 m 4488.96443624 m
Image shape: (720, 1280, 3)
 40%|████      | 505/1261 [02:50<04:16,  2.95it/s]
5289.03727868 m 5700.1355212 m 5494.58639994 m
Image shape: (720, 1280, 3)
 40%|████      | 506/1261 [02:50<04:15,  2.96it/s]
8183.28524602 m 12101.1355476 m 10142.2103968 m
Image shape: (720, 1280, 3)
 40%|████      | 507/1261 [02:51<04:32,  2.77it/s]
5336.20789743 m 2669.94919714 m 4003.07854728 m
Image shape: (720, 1280, 3)
 40%|████      | 508/1261 [02:51<04:27,  2.81it/s]
18265.7923282 m 4086.38442663 m 11176.0883774 m
Image shape: (720, 1280, 3)
 40%|████      | 509/1261 [02:52<04:23,  2.85it/s]
5213.84245649 m 2594.79523538 m 3904.31884593 m
Image shape: (720, 1280, 3)
 40%|████      | 510/1261 [02:52<04:19,  2.89it/s]
7612.61237202 m 6865.6686842 m 7239.14052811 m
Image shape: (720, 1280, 3)
 41%|████      | 511/1261 [02:52<04:17,  2.91it/s]
4494.89548101 m 3621.88009097 m 4058.38778599 m
Image shape: (720, 1280, 3)
 41%|████      | 512/1261 [02:53<04:19,  2.88it/s]
5929.60957352 m 2102.57574016 m 4016.09265684 m
Image shape: (720, 1280, 3)
 41%|████      | 513/1261 [02:53<04:21,  2.86it/s]
6504.68309526 m 1556.14955071 m 4030.41632299 m
Image shape: (720, 1280, 3)
 41%|████      | 514/1261 [02:53<04:18,  2.88it/s]
10883.5526986 m 8137.71865172 m 9510.63567515 m
Image shape: (720, 1280, 3)
 41%|████      | 515/1261 [02:54<04:16,  2.91it/s]
15733.5348273 m 3541.14611444 m 9637.34047088 m
Image shape: (720, 1280, 3)
 41%|████      | 516/1261 [02:54<04:16,  2.91it/s]
9524.4105628 m 3916.7290184 m 6720.5697906 m
Image shape: (720, 1280, 3)
 41%|████      | 517/1261 [02:54<04:14,  2.92it/s]
13573.6615854 m 2200.70573248 m 7887.18365892 m
Image shape: (720, 1280, 3)
 41%|████      | 518/1261 [02:55<04:16,  2.90it/s]
2057.21447574 m 3833.79004533 m 2945.50226053 m
Image shape: (720, 1280, 3)
 41%|████      | 519/1261 [02:55<04:13,  2.93it/s]
3451.39655799 m 11059.6432029 m 7255.51988045 m
Image shape: (720, 1280, 3)
 41%|████      | 520/1261 [02:55<04:13,  2.92it/s]
3607.41016547 m 9702.90674385 m 6655.15845466 m
Image shape: (720, 1280, 3)
 41%|████▏     | 521/1261 [02:56<04:17,  2.87it/s]
4696.29064445 m 8439.78248995 m 6568.0365672 m
Image shape: (720, 1280, 3)
 41%|████▏     | 522/1261 [02:56<04:20,  2.83it/s]
6080.28857645 m 3314.97575676 m 4697.63216661 m
Image shape: (720, 1280, 3)
 41%|████▏     | 523/1261 [02:56<04:23,  2.80it/s]
46285.6558267 m 1383.70817595 m 23834.6820013 m
Image shape: (720, 1280, 3)
 42%|████▏     | 524/1261 [02:57<04:18,  2.85it/s]
4965.51476748 m 1089.96026738 m 3027.73751743 m
Image shape: (720, 1280, 3)
 42%|████▏     | 525/1261 [02:57<04:14,  2.89it/s]
7069.20443658 m 7841.77055772 m 7455.48749715 m
Image shape: (720, 1280, 3)
 42%|████▏     | 526/1261 [02:57<04:10,  2.93it/s]
33206.0611508 m 2730.2165561 m 17968.1388534 m
Image shape: (720, 1280, 3)
 42%|████▏     | 527/1261 [02:58<04:08,  2.95it/s]
6421.00356973 m 53799.992662 m 30110.4981159 m
Image shape: (720, 1280, 3)
 42%|████▏     | 528/1261 [02:58<04:05,  2.98it/s]
3733.01123096 m 11157.9735692 m 7445.49240009 m
Image shape: (720, 1280, 3)
 42%|████▏     | 529/1261 [02:58<04:05,  2.98it/s]
12781.2698529 m 3665.35592206 m 8223.31288747 m
Image shape: (720, 1280, 3)
 42%|████▏     | 530/1261 [02:59<04:04,  2.99it/s]
11466.5244925 m 3329.37189994 m 7397.94819622 m
Image shape: (720, 1280, 3)
 42%|████▏     | 531/1261 [02:59<04:04,  2.98it/s]
4479.09556055 m 3348.16449711 m 3913.63002883 m
Image shape: (720, 1280, 3)
 42%|████▏     | 532/1261 [02:59<04:06,  2.95it/s]
4317.20315508 m 3631.24448834 m 3974.22382171 m
Image shape: (720, 1280, 3)
 42%|████▏     | 533/1261 [03:00<04:06,  2.95it/s]
1968.82486741 m 5530.87513591 m 3749.85000166 m
Image shape: (720, 1280, 3)
 42%|████▏     | 534/1261 [03:00<04:08,  2.93it/s]
1177.42336635 m 1486.08055845 m 1331.7519624 m
Image shape: (720, 1280, 3)
 42%|████▏     | 535/1261 [03:00<04:07,  2.94it/s]
1140.51105424 m 1028.02936343 m 1084.27020883 m
Image shape: (720, 1280, 3)
 43%|████▎     | 536/1261 [03:01<04:06,  2.94it/s]
1345.39776634 m 879.696368403 m 1112.54706737 m
Image shape: (720, 1280, 3)
 43%|████▎     | 537/1261 [03:01<04:11,  2.87it/s]
1155.48666557 m 490.48628977 m 822.986477672 m
Image shape: (720, 1280, 3)
 43%|████▎     | 538/1261 [03:02<04:14,  2.85it/s]
1457.81723108 m 460.18152153 m 958.999376304 m
Image shape: (720, 1280, 3)
 43%|████▎     | 539/1261 [03:02<04:18,  2.80it/s]
899.181524435 m 304.970959035 m 602.076241735 m
Image shape: (720, 1280, 3)
 43%|████▎     | 540/1261 [03:02<04:15,  2.82it/s]
712.031000305 m 329.770678047 m 520.900839176 m
Image shape: (720, 1280, 3)
 43%|████▎     | 541/1261 [03:03<04:18,  2.79it/s]
675.906135188 m 584.355881959 m 630.131008573 m
Image shape: (720, 1280, 3)
 43%|████▎     | 542/1261 [03:03<04:18,  2.78it/s]
808.991744838 m 776.735282281 m 792.86351356 m
Image shape: (720, 1280, 3)
 43%|████▎     | 543/1261 [03:03<04:18,  2.78it/s]
1028.71083371 m 986.398049014 m 1007.55444136 m
Image shape: (720, 1280, 3)
 43%|████▎     | 544/1261 [03:04<04:18,  2.77it/s]
970.718323931 m 23435.7038996 m 12203.2111118 m
Image shape: (720, 1280, 3)
 43%|████▎     | 545/1261 [03:04<04:17,  2.78it/s]
1345.20586916 m 10179.0567808 m 5762.13132498 m
Image shape: (720, 1280, 3)
 43%|████▎     | 546/1261 [03:04<04:18,  2.77it/s]
1811.7229642 m 3413.96238419 m 2612.84267419 m
Image shape: (720, 1280, 3)
 43%|████▎     | 547/1261 [03:05<04:18,  2.76it/s]
2786.99276681 m 4646.32172251 m 3716.65724466 m
Image shape: (720, 1280, 3)
 43%|████▎     | 548/1261 [03:05<04:19,  2.75it/s]
2742.41155211 m 3238.34177977 m 2990.37666594 m
Image shape: (720, 1280, 3)
 44%|████▎     | 549/1261 [03:06<04:21,  2.73it/s]
4987.38640265 m 724.055543995 m 2855.72097332 m
Image shape: (720, 1280, 3)
 44%|████▎     | 550/1261 [03:06<04:24,  2.69it/s]
2190.61156608 m 741.574420518 m 1466.0929933 m
Image shape: (720, 1280, 3)
 44%|████▎     | 551/1261 [03:06<04:24,  2.68it/s]
1379.61574794 m 449.80877566 m 914.712261801 m
Image shape: (720, 1280, 3)
 44%|████▍     | 552/1261 [03:07<04:26,  2.66it/s]
2228.39519203 m 548.367166555 m 1388.38117929 m
Image shape: (720, 1280, 3)
 44%|████▍     | 553/1261 [03:07<04:28,  2.64it/s]
1498.6809526 m 454.799407219 m 976.74017991 m
Image shape: (720, 1280, 3)
 44%|████▍     | 554/1261 [03:07<04:27,  2.65it/s]
1110.95106245 m 991.416037574 m 1051.18355001 m
Image shape: (720, 1280, 3)
 44%|████▍     | 555/1261 [03:08<04:25,  2.66it/s]
1231.0131563 m 1465.98326433 m 1348.49821032 m
Image shape: (720, 1280, 3)
 44%|████▍     | 556/1261 [03:08<04:22,  2.69it/s]
810.632234409 m 1021.73676853 m 916.184501468 m
Image shape: (720, 1280, 3)
 44%|████▍     | 557/1261 [03:09<04:18,  2.72it/s]
2362.87654905 m 526.811015679 m 1444.84378237 m
Image shape: (720, 1280, 3)
 44%|████▍     | 558/1261 [03:09<04:15,  2.76it/s]
1178.41051731 m 497.248462663 m 837.829489986 m
Image shape: (720, 1280, 3)
 44%|████▍     | 559/1261 [03:09<04:12,  2.79it/s]
1859.10032471 m 359.0676979 m 1109.08401131 m
Image shape: (720, 1280, 3)
 44%|████▍     | 560/1261 [03:10<04:10,  2.80it/s]
989.397554174 m 468.361273601 m 728.879413888 m
Image shape: (720, 1280, 3)
 44%|████▍     | 561/1261 [03:10<04:08,  2.82it/s]
839.92739942 m 611.206878244 m 725.567138832 m
Image shape: (720, 1280, 3)
 45%|████▍     | 562/1261 [03:10<04:07,  2.82it/s]
1692.4739536 m 698.578619258 m 1195.52628643 m
Image shape: (720, 1280, 3)
 45%|████▍     | 563/1261 [03:11<04:07,  2.82it/s]
10468.0341133 m 924.483381437 m 5696.25874735 m
Image shape: (720, 1280, 3)
 45%|████▍     | 564/1261 [03:11<04:04,  2.85it/s]
3886.87998783 m 1064.7065859 m 2475.79328687 m
Image shape: (720, 1280, 3)
 45%|████▍     | 565/1261 [03:11<04:12,  2.76it/s]
2386.98594148 m 530.722893456 m 1458.85441747 m
Image shape: (720, 1280, 3)
 45%|████▍     | 566/1261 [03:12<04:10,  2.77it/s]
790.87974621 m 468.61823478 m 629.748990495 m
Image shape: (720, 1280, 3)
 45%|████▍     | 567/1261 [03:12<04:05,  2.83it/s]
1638.05572686 m 421.178670905 m 1029.61719888 m
Image shape: (720, 1280, 3)
 45%|████▌     | 568/1261 [03:12<04:01,  2.87it/s]
6371.45092594 m 463.870057648 m 3417.66049179 m
Image shape: (720, 1280, 3)
 45%|████▌     | 569/1261 [03:13<03:57,  2.91it/s]
16238.0772599 m 386.38532089 m 8312.23129041 m
Image shape: (720, 1280, 3)
 45%|████▌     | 570/1261 [03:13<03:55,  2.94it/s]
24686.8316343 m 412.853916739 m 12549.8427755 m
Image shape: (720, 1280, 3)
 45%|████▌     | 571/1261 [03:13<03:53,  2.96it/s]
14465.5908413 m 331.359888926 m 7398.47536511 m
Image shape: (720, 1280, 3)
 45%|████▌     | 572/1261 [03:14<03:53,  2.96it/s]
58380.0628726 m 404.538112142 m 29392.3004924 m
Image shape: (720, 1280, 3)
 45%|████▌     | 573/1261 [03:14<03:52,  2.97it/s]
9837.30018423 m 754.764889377 m 5296.03253681 m
Image shape: (720, 1280, 3)
 46%|████▌     | 574/1261 [03:14<03:52,  2.96it/s]
2925.15219855 m 3348.42938423 m 3136.79079139 m
Image shape: (720, 1280, 3)
 46%|████▌     | 575/1261 [03:15<03:50,  2.97it/s]
4853.51725703 m 4893.5338774 m 4873.52556722 m
Image shape: (720, 1280, 3)
 46%|████▌     | 576/1261 [03:15<03:50,  2.98it/s]
14042.3041432 m 2370.10590927 m 8206.20502623 m
Image shape: (720, 1280, 3)
 46%|████▌     | 577/1261 [03:15<03:50,  2.96it/s]
8629.3641652 m 671.203660553 m 4650.28391288 m
Image shape: (720, 1280, 3)
 46%|████▌     | 578/1261 [03:16<03:50,  2.97it/s]
8688.06778402 m 554.162102236 m 4621.11494313 m
Image shape: (720, 1280, 3)
 46%|████▌     | 579/1261 [03:16<03:49,  2.97it/s]
17203.5124233 m 1307.60276627 m 9255.55759477 m
Image shape: (720, 1280, 3)
 46%|████▌     | 580/1261 [03:16<03:49,  2.97it/s]
8693.7380412 m 1089.65578694 m 4891.69691407 m
Image shape: (720, 1280, 3)
 46%|████▌     | 581/1261 [03:17<03:49,  2.97it/s]
6222.5417893 m 519.808939806 m 3371.17536455 m
Image shape: (720, 1280, 3)
 46%|████▌     | 582/1261 [03:17<03:49,  2.96it/s]
5646.71271279 m 368.564787206 m 3007.63875 m
Image shape: (720, 1280, 3)
 46%|████▌     | 583/1261 [03:17<03:49,  2.96it/s]
5045.33756505 m 509.00275113 m 2777.17015809 m
Image shape: (720, 1280, 3)
 46%|████▋     | 584/1261 [03:18<03:47,  2.97it/s]
2488.82188262 m 471.762813167 m 1480.2923479 m
Image shape: (720, 1280, 3)
 46%|████▋     | 585/1261 [03:18<03:46,  2.98it/s]
2038.11756578 m 877.202035022 m 1457.6598004 m
Image shape: (720, 1280, 3)
 46%|████▋     | 586/1261 [03:18<03:48,  2.96it/s]
2620.39960357 m 1429.61076001 m 2025.00518179 m
Image shape: (720, 1280, 3)
 47%|████▋     | 587/1261 [03:19<03:46,  2.98it/s]
2589.58483747 m 26479.8938507 m 14534.7393441 m
Image shape: (720, 1280, 3)
 47%|████▋     | 588/1261 [03:19<03:45,  2.99it/s]
2519.23954123 m 5606.16229147 m 4062.70091635 m
Image shape: (720, 1280, 3)
 47%|████▋     | 589/1261 [03:19<03:45,  2.98it/s]
9422.68820851 m 390.68304202 m 4906.68562526 m
Image shape: (720, 1280, 3)
 47%|████▋     | 590/1261 [03:20<03:45,  2.98it/s]
1825.80010754 m 401.927605576 m 1113.86385656 m
Image shape: (720, 1280, 3)
 47%|████▋     | 591/1261 [03:20<03:45,  2.97it/s]
3033.20676618 m 435.347065343 m 1734.27691576 m
Image shape: (720, 1280, 3)
 47%|████▋     | 592/1261 [03:21<03:45,  2.97it/s]
4305.83741922 m 532.413326837 m 2419.12537303 m
Image shape: (720, 1280, 3)
 47%|████▋     | 593/1261 [03:21<03:44,  2.98it/s]
75493.4034075 m 455.996709124 m 37974.7000583 m
Image shape: (720, 1280, 3)
 47%|████▋     | 594/1261 [03:21<03:44,  2.98it/s]
4063.00208238 m 314.30175778 m 2188.65192008 m
Image shape: (720, 1280, 3)
 47%|████▋     | 595/1261 [03:22<03:47,  2.92it/s]
3923.26618058 m 478.679226504 m 2200.97270354 m
Image shape: (720, 1280, 3)
 47%|████▋     | 596/1261 [03:22<03:50,  2.89it/s]
8267.50964179 m 534.118500703 m 4400.81407125 m
Image shape: (720, 1280, 3)
 47%|████▋     | 597/1261 [03:22<03:52,  2.85it/s]
79402.593793 m 651.14471919 m 40026.8692561 m
Image shape: (720, 1280, 3)
 47%|████▋     | 598/1261 [03:23<03:50,  2.88it/s]
27445.2054575 m 374.115198253 m 13909.6603279 m
Image shape: (720, 1280, 3)
 48%|████▊     | 599/1261 [03:23<03:47,  2.91it/s]
11546.7566409 m 199.469710077 m 5873.11317548 m
Image shape: (720, 1280, 3)
 48%|████▊     | 600/1261 [03:23<03:45,  2.92it/s]
24554.1742347 m 136.434227766 m 12345.3042313 m
Image shape: (720, 1280, 3)
 48%|████▊     | 601/1261 [03:24<03:43,  2.96it/s]
1525.90727496 m 121.735384305 m 823.821329634 m
Image shape: (720, 1280, 3)
 48%|████▊     | 602/1261 [03:24<03:43,  2.95it/s]
2006.35289454 m 254.63639137 m 1130.49464295 m
Image shape: (720, 1280, 3)
 48%|████▊     | 603/1261 [03:24<03:42,  2.95it/s]
5748.05808724 m 247.322791968 m 2997.69043961 m
Image shape: (720, 1280, 3)
 48%|████▊     | 604/1261 [03:25<03:41,  2.96it/s]
24402.049067 m 224.703644841 m 12313.3763559 m
Image shape: (720, 1280, 3)
 48%|████▊     | 605/1261 [03:25<03:39,  2.98it/s]
2227.9854216 m 454.651492918 m 1341.31845726 m
Image shape: (720, 1280, 3)
 48%|████▊     | 606/1261 [03:25<03:38,  3.00it/s]
967.514229022 m 593.405644178 m 780.4599366 m
Image shape: (720, 1280, 3)
 48%|████▊     | 607/1261 [03:26<03:37,  3.00it/s]
1041.08759814 m 622.105555557 m 831.596576846 m
Image shape: (720, 1280, 3)
 48%|████▊     | 608/1261 [03:26<03:37,  3.00it/s]
1378.4108973 m 660.149199974 m 1019.28004864 m
Image shape: (720, 1280, 3)
 48%|████▊     | 609/1261 [03:26<03:38,  2.99it/s]
1640.59826109 m 784.267521793 m 1212.43289144 m
Image shape: (720, 1280, 3)
 48%|████▊     | 610/1261 [03:27<03:37,  2.99it/s]
915.095907333 m 1077.39998215 m 996.247944743 m
Image shape: (720, 1280, 3)
 48%|████▊     | 611/1261 [03:27<03:36,  3.00it/s]
939.005701582 m 831.693776273 m 885.349738927 m
Image shape: (720, 1280, 3)
 49%|████▊     | 612/1261 [03:27<03:36,  3.00it/s]
774.470304235 m 377.192752558 m 575.831528397 m
Image shape: (720, 1280, 3)
 49%|████▊     | 613/1261 [03:28<03:36,  2.99it/s]
810.389439041 m 387.559916068 m 598.974677554 m
Image shape: (720, 1280, 3)
 49%|████▊     | 614/1261 [03:28<03:36,  2.99it/s]
1076.26002232 m 393.902081911 m 735.081052114 m
Image shape: (720, 1280, 3)
 49%|████▉     | 615/1261 [03:28<03:35,  3.00it/s]
1010.23058721 m 383.218083906 m 696.724335557 m
Image shape: (720, 1280, 3)
 49%|████▉     | 616/1261 [03:29<03:34,  3.01it/s]
661.548408002 m 571.140764421 m 616.344586211 m
Image shape: (720, 1280, 3)
 49%|████▉     | 617/1261 [03:29<03:33,  3.02it/s]
409.942073409 m 1041.09999007 m 725.52103174 m
Image shape: (720, 1280, 3)
 49%|████▉     | 618/1261 [03:29<03:33,  3.01it/s]
412.641793496 m 759.444922333 m 586.043357915 m
Image shape: (720, 1280, 3)
 49%|████▉     | 619/1261 [03:30<03:33,  3.01it/s]
323.654026421 m 799.788920339 m 561.72147338 m
Image shape: (720, 1280, 3)
 49%|████▉     | 620/1261 [03:30<03:32,  3.01it/s]
408.644444694 m 830.894456808 m 619.769450751 m
Image shape: (720, 1280, 3)
 49%|████▉     | 621/1261 [03:30<03:32,  3.02it/s]
492.802439907 m 732.224023296 m 612.513231601 m
Image shape: (720, 1280, 3)
 49%|████▉     | 622/1261 [03:31<03:31,  3.02it/s]
476.940886501 m 1234.90400916 m 855.922447828 m
Image shape: (720, 1280, 3)
 49%|████▉     | 623/1261 [03:31<03:31,  3.01it/s]
447.585814678 m 1977.56530802 m 1212.57556135 m
Image shape: (720, 1280, 3)
 49%|████▉     | 624/1261 [03:31<03:30,  3.02it/s]
417.039447638 m 1300.94158882 m 858.990518227 m
Image shape: (720, 1280, 3)
 50%|████▉     | 625/1261 [03:32<03:31,  3.01it/s]
321.513197619 m 1345.29327206 m 833.403234841 m
Image shape: (720, 1280, 3)
 50%|████▉     | 626/1261 [03:32<03:29,  3.03it/s]
384.467570421 m 1317.22567189 m 850.846621155 m
Image shape: (720, 1280, 3)
 50%|████▉     | 627/1261 [03:32<03:28,  3.04it/s]
438.261808609 m 651.58412967 m 544.92296914 m
Image shape: (720, 1280, 3)
 50%|████▉     | 628/1261 [03:33<03:27,  3.05it/s]
436.582453074 m 516.843511772 m 476.712982423 m
Image shape: (720, 1280, 3)
 50%|████▉     | 629/1261 [03:33<03:26,  3.06it/s]
456.384575826 m 281.356010838 m 368.870293332 m
Image shape: (720, 1280, 3)
 50%|████▉     | 630/1261 [03:33<03:26,  3.06it/s]
505.522256454 m 268.35233677 m 386.937296612 m
Image shape: (720, 1280, 3)
 50%|█████     | 631/1261 [03:34<03:26,  3.04it/s]
616.77207377 m 311.752578474 m 464.262326122 m
Image shape: (720, 1280, 3)
 50%|█████     | 632/1261 [03:34<03:27,  3.03it/s]
645.519093372 m 341.662322195 m 493.590707784 m
Image shape: (720, 1280, 3)
 50%|█████     | 633/1261 [03:34<03:27,  3.03it/s]
646.135692545 m 428.457318288 m 537.296505416 m
Image shape: (720, 1280, 3)
 50%|█████     | 634/1261 [03:35<03:28,  3.01it/s]
571.864495623 m 381.048687254 m 476.456591438 m
Image shape: (720, 1280, 3)
 50%|█████     | 635/1261 [03:35<03:27,  3.02it/s]
552.643499277 m 582.736678716 m 567.690088996 m
Image shape: (720, 1280, 3)
 50%|█████     | 636/1261 [03:35<03:26,  3.02it/s]
502.574986443 m 784.744226734 m 643.659606588 m
Image shape: (720, 1280, 3)
 51%|█████     | 637/1261 [03:36<03:26,  3.02it/s]
457.686673928 m 648.415429133 m 553.051051531 m
Image shape: (720, 1280, 3)
 51%|█████     | 638/1261 [03:36<03:26,  3.02it/s]
480.460128348 m 558.623254328 m 519.541691338 m
Image shape: (720, 1280, 3)
 51%|█████     | 639/1261 [03:36<03:26,  3.01it/s]
532.536887369 m 599.435419014 m 565.986153191 m
Image shape: (720, 1280, 3)
 51%|█████     | 640/1261 [03:37<03:26,  3.01it/s]
599.113617083 m 404.166138575 m 501.639877829 m
Image shape: (720, 1280, 3)
 51%|█████     | 641/1261 [03:37<03:25,  3.02it/s]
673.962277191 m 371.634570016 m 522.798423603 m
Image shape: (720, 1280, 3)
 51%|█████     | 642/1261 [03:37<03:25,  3.01it/s]
714.158539444 m 285.613737595 m 499.88613852 m
Image shape: (720, 1280, 3)
 51%|█████     | 643/1261 [03:38<03:23,  3.03it/s]
782.194445927 m 317.357068787 m 549.775757357 m
Image shape: (720, 1280, 3)
 51%|█████     | 644/1261 [03:38<03:24,  3.02it/s]
829.506997549 m 305.863282682 m 567.685140116 m
Image shape: (720, 1280, 3)
 51%|█████     | 645/1261 [03:38<03:23,  3.03it/s]
879.415593847 m 346.052309927 m 612.733951887 m
Image shape: (720, 1280, 3)
 51%|█████     | 646/1261 [03:39<03:24,  3.01it/s]
739.470878921 m 309.452430523 m 524.461654722 m
Image shape: (720, 1280, 3)
 51%|█████▏    | 647/1261 [03:39<03:23,  3.01it/s]
762.164090622 m 295.124176988 m 528.644133805 m
Image shape: (720, 1280, 3)
 51%|█████▏    | 648/1261 [03:39<03:23,  3.01it/s]
777.75290988 m 452.912587958 m 615.332748919 m
Image shape: (720, 1280, 3)
 51%|█████▏    | 649/1261 [03:40<03:23,  3.01it/s]
723.540371812 m 734.306738694 m 728.923555253 m
Image shape: (720, 1280, 3)
 52%|█████▏    | 650/1261 [03:40<03:23,  3.01it/s]
814.869337286 m 856.814361385 m 835.841849336 m
Image shape: (720, 1280, 3)
 52%|█████▏    | 651/1261 [03:40<03:22,  3.01it/s]
779.579392878 m 658.516714857 m 719.048053868 m
Image shape: (720, 1280, 3)
 52%|█████▏    | 652/1261 [03:41<03:22,  3.01it/s]
716.82688522 m 456.982533583 m 586.904709401 m
Image shape: (720, 1280, 3)
 52%|█████▏    | 653/1261 [03:41<03:20,  3.03it/s]
641.430072272 m 404.359604637 m 522.894838454 m
Image shape: (720, 1280, 3)
 52%|█████▏    | 654/1261 [03:41<03:20,  3.03it/s]
596.422375966 m 267.134676216 m 431.778526091 m
Image shape: (720, 1280, 3)
 52%|█████▏    | 655/1261 [03:41<03:21,  3.01it/s]
524.168261973 m 290.022523652 m 407.095392813 m
Image shape: (720, 1280, 3)
 52%|█████▏    | 656/1261 [03:42<03:20,  3.02it/s]
507.625476907 m 287.355180826 m 397.490328867 m
Image shape: (720, 1280, 3)
 52%|█████▏    | 657/1261 [03:42<03:21,  2.99it/s]
501.507084622 m 335.9109107 m 418.708997661 m
Image shape: (720, 1280, 3)
 52%|█████▏    | 658/1261 [03:43<03:21,  2.99it/s]
491.644563474 m 458.870829661 m 475.257696568 m
Image shape: (720, 1280, 3)
 52%|█████▏    | 659/1261 [03:43<03:21,  2.99it/s]
517.823780451 m 371.042364345 m 444.433072398 m
Image shape: (720, 1280, 3)
 52%|█████▏    | 660/1261 [03:43<03:20,  3.00it/s]
481.022196284 m 504.478759707 m 492.750477996 m
Image shape: (720, 1280, 3)
 52%|█████▏    | 661/1261 [03:44<03:20,  3.00it/s]
502.515889546 m 663.708767217 m 583.112328382 m
Image shape: (720, 1280, 3)
 52%|█████▏    | 662/1261 [03:44<03:19,  3.00it/s]
504.720422501 m 719.574549411 m 612.147485956 m
Image shape: (720, 1280, 3)
 53%|█████▎    | 663/1261 [03:44<03:19,  3.00it/s]
514.590308562 m 953.06389345 m 733.827101006 m
Image shape: (720, 1280, 3)
 53%|█████▎    | 664/1261 [03:45<03:18,  3.00it/s]
489.884253656 m 896.45526722 m 693.169760438 m
Image shape: (720, 1280, 3)
 53%|█████▎    | 665/1261 [03:45<03:18,  3.00it/s]
500.520551825 m 502.005048495 m 501.26280016 m
Image shape: (720, 1280, 3)
 53%|█████▎    | 666/1261 [03:45<03:17,  3.01it/s]
545.105343072 m 415.418366518 m 480.261854795 m
Image shape: (720, 1280, 3)
 53%|█████▎    | 667/1261 [03:45<03:16,  3.02it/s]
535.266857584 m 297.977463893 m 416.622160739 m
Image shape: (720, 1280, 3)
 53%|█████▎    | 668/1261 [03:46<03:16,  3.02it/s]
526.141014433 m 325.161308233 m 425.651161333 m
Image shape: (720, 1280, 3)
 53%|█████▎    | 669/1261 [03:46<03:15,  3.02it/s]
610.972424621 m 326.094738936 m 468.533581779 m
Image shape: (720, 1280, 3)
 53%|█████▎    | 670/1261 [03:46<03:15,  3.02it/s]
684.297981462 m 324.471343482 m 504.384662472 m
Image shape: (720, 1280, 3)
 53%|█████▎    | 671/1261 [03:47<03:15,  3.02it/s]
695.591478669 m 336.744607999 m 516.168043334 m
Image shape: (720, 1280, 3)
 53%|█████▎    | 672/1261 [03:47<03:14,  3.02it/s]
778.078994264 m 357.532086895 m 567.805540579 m
Image shape: (720, 1280, 3)
 53%|█████▎    | 673/1261 [03:47<03:17,  2.98it/s]
753.511868167 m 416.335319376 m 584.923593772 m
Image shape: (720, 1280, 3)
 53%|█████▎    | 674/1261 [03:48<03:20,  2.93it/s]
739.89455742 m 612.261850259 m 676.07820384 m
Image shape: (720, 1280, 3)
 54%|█████▎    | 675/1261 [03:48<03:23,  2.89it/s]
776.900334368 m 740.243261823 m 758.571798096 m
Image shape: (720, 1280, 3)
 54%|█████▎    | 676/1261 [03:49<03:22,  2.88it/s]
721.917392134 m 732.514122559 m 727.215757346 m
Image shape: (720, 1280, 3)
 54%|█████▎    | 677/1261 [03:49<03:20,  2.91it/s]
777.749246308 m 534.677489151 m 656.21336773 m
Image shape: (720, 1280, 3)
 54%|█████▍    | 678/1261 [03:49<03:17,  2.95it/s]
872.293148892 m 480.724242381 m 676.508695637 m
Image shape: (720, 1280, 3)
 54%|█████▍    | 679/1261 [03:50<03:16,  2.95it/s]
836.485184562 m 309.153042269 m 572.819113416 m
Image shape: (720, 1280, 3)
 54%|█████▍    | 680/1261 [03:50<03:15,  2.98it/s]
897.077441653 m 420.520208905 m 658.798825279 m
Image shape: (720, 1280, 3)
 54%|█████▍    | 681/1261 [03:50<03:13,  2.99it/s]
938.090498148 m 466.842981322 m 702.466739735 m
Image shape: (720, 1280, 3)
 54%|█████▍    | 682/1261 [03:51<03:12,  3.01it/s]
1023.83559112 m 482.20069699 m 753.018144054 m
Image shape: (720, 1280, 3)
 54%|█████▍    | 683/1261 [03:51<03:12,  3.00it/s]
1093.73867129 m 905.193460679 m 999.466065984 m
Image shape: (720, 1280, 3)
 54%|█████▍    | 684/1261 [03:51<03:11,  3.01it/s]
1045.36777211 m 348.802847213 m 697.085309663 m
Image shape: (720, 1280, 3)
 54%|█████▍    | 685/1261 [03:52<03:12,  3.00it/s]
946.446625884 m 377.241977689 m 661.844301786 m
Image shape: (720, 1280, 3)
 54%|█████▍    | 686/1261 [03:52<03:10,  3.01it/s]
818.169065838 m 523.434107872 m 670.801586855 m
Image shape: (720, 1280, 3)
 54%|█████▍    | 687/1261 [03:52<03:10,  3.01it/s]
691.073175846 m 655.745386753 m 673.4092813 m
Image shape: (720, 1280, 3)
 55%|█████▍    | 688/1261 [03:53<03:09,  3.02it/s]
765.224790818 m 721.128522649 m 743.176656733 m
Image shape: (720, 1280, 3)
 55%|█████▍    | 689/1261 [03:53<03:09,  3.02it/s]
732.283786541 m 780.834507031 m 756.559146786 m
Image shape: (720, 1280, 3)
 55%|█████▍    | 690/1261 [03:53<03:08,  3.03it/s]
593.372772718 m 475.590448694 m 534.481610706 m
Image shape: (720, 1280, 3)
 55%|█████▍    | 691/1261 [03:54<03:07,  3.05it/s]
599.085186217 m 440.603953545 m 519.844569881 m
Image shape: (720, 1280, 3)
 55%|█████▍    | 692/1261 [03:54<03:06,  3.05it/s]
555.591923788 m 344.68578343 m 450.138853609 m
Image shape: (720, 1280, 3)
 55%|█████▍    | 693/1261 [03:54<03:06,  3.05it/s]
541.76914582 m 503.656594147 m 522.712869983 m
Image shape: (720, 1280, 3)
 55%|█████▌    | 694/1261 [03:55<03:06,  3.04it/s]
548.849721713 m 409.869137518 m 479.359429615 m
Image shape: (720, 1280, 3)
 55%|█████▌    | 695/1261 [03:55<03:06,  3.04it/s]
537.580444621 m 727.28757022 m 632.434007421 m
Image shape: (720, 1280, 3)
 55%|█████▌    | 696/1261 [03:55<03:05,  3.04it/s]
547.606335753 m 771.9799091 m 659.793122427 m
Image shape: (720, 1280, 3)
 55%|█████▌    | 697/1261 [03:56<03:06,  3.03it/s]
531.070085669 m 514.548355126 m 522.809220398 m
Image shape: (720, 1280, 3)
 55%|█████▌    | 698/1261 [03:56<03:05,  3.03it/s]
536.455062241 m 712.338708887 m 624.396885564 m
Image shape: (720, 1280, 3)
 55%|█████▌    | 699/1261 [03:56<03:06,  3.02it/s]
548.826150668 m 819.261418505 m 684.043784586 m
Image shape: (720, 1280, 3)
 56%|█████▌    | 700/1261 [03:56<03:05,  3.02it/s]
523.979047466 m 843.386935588 m 683.682991527 m
Image shape: (720, 1280, 3)
 56%|█████▌    | 701/1261 [03:57<03:04,  3.03it/s]
526.040977932 m 615.971765581 m 571.006371757 m
Image shape: (720, 1280, 3)
 56%|█████▌    | 702/1261 [03:57<03:04,  3.03it/s]
531.760919478 m 605.210383419 m 568.485651449 m
Image shape: (720, 1280, 3)
 56%|█████▌    | 703/1261 [03:57<03:04,  3.03it/s]
522.38788884 m 422.939757983 m 472.663823411 m
Image shape: (720, 1280, 3)
 56%|█████▌    | 704/1261 [03:58<03:03,  3.03it/s]
547.147094097 m 466.672236742 m 506.909665419 m
Image shape: (720, 1280, 3)
 56%|█████▌    | 705/1261 [03:58<03:03,  3.03it/s]
525.93018855 m 571.462624957 m 548.696406753 m
Image shape: (720, 1280, 3)
 56%|█████▌    | 706/1261 [03:58<03:04,  3.00it/s]
579.38617948 m 413.858297908 m 496.622238694 m
Image shape: (720, 1280, 3)
 56%|█████▌    | 707/1261 [03:59<03:03,  3.02it/s]
594.722180893 m 912.849010051 m 753.785595472 m
Image shape: (720, 1280, 3)
 56%|█████▌    | 708/1261 [03:59<03:03,  3.01it/s]
622.458276662 m 401.812575401 m 512.135426032 m
Image shape: (720, 1280, 3)
 56%|█████▌    | 709/1261 [03:59<03:02,  3.02it/s]
600.755791447 m 497.20154475 m 548.978668099 m
Image shape: (720, 1280, 3)
 56%|█████▋    | 710/1261 [04:00<03:02,  3.03it/s]
606.739668776 m 554.339240214 m 580.539454495 m
Image shape: (720, 1280, 3)
 56%|█████▋    | 711/1261 [04:00<03:01,  3.03it/s]
698.069429055 m 699.858823162 m 698.964126109 m
Image shape: (720, 1280, 3)
 56%|█████▋    | 712/1261 [04:00<03:00,  3.03it/s]
721.334381727 m 793.664806266 m 757.499593997 m
Image shape: (720, 1280, 3)
 57%|█████▋    | 713/1261 [04:01<03:00,  3.04it/s]
689.123145278 m 810.308109588 m 749.715627433 m
Image shape: (720, 1280, 3)
 57%|█████▋    | 714/1261 [04:01<03:00,  3.03it/s]
646.271749924 m 528.408147584 m 587.339948754 m
Image shape: (720, 1280, 3)
 57%|█████▋    | 715/1261 [04:01<03:00,  3.02it/s]
668.906733534 m 444.606791683 m 556.756762609 m
Image shape: (720, 1280, 3)
 57%|█████▋    | 716/1261 [04:02<02:59,  3.04it/s]
631.646211529 m 357.37128326 m 494.508747395 m
Image shape: (720, 1280, 3)
 57%|█████▋    | 717/1261 [04:02<02:58,  3.04it/s]
618.839176978 m 358.180563996 m 488.509870487 m
Image shape: (720, 1280, 3)
 57%|█████▋    | 718/1261 [04:02<02:57,  3.05it/s]
688.681932474 m 429.724297521 m 559.203114998 m
Image shape: (720, 1280, 3)
 57%|█████▋    | 719/1261 [04:03<02:57,  3.05it/s]
709.58017786 m 417.221124572 m 563.400651216 m
Image shape: (720, 1280, 3)
 57%|█████▋    | 720/1261 [04:03<02:58,  3.03it/s]
699.317490659 m 498.273920617 m 598.795705638 m
Image shape: (720, 1280, 3)
 57%|█████▋    | 721/1261 [04:03<02:59,  3.02it/s]
718.523767888 m 433.456997264 m 575.990382576 m
Image shape: (720, 1280, 3)
 57%|█████▋    | 722/1261 [04:04<02:58,  3.02it/s]
654.698231112 m 1502.3899655 m 1078.5440983 m
Image shape: (720, 1280, 3)
 57%|█████▋    | 723/1261 [04:04<02:58,  3.02it/s]
677.681283493 m 574.380897261 m 626.031090377 m
Image shape: (720, 1280, 3)
 57%|█████▋    | 724/1261 [04:04<02:57,  3.02it/s]
680.628124271 m 846.047817614 m 763.337970943 m
Image shape: (720, 1280, 3)
 57%|█████▋    | 725/1261 [04:05<02:57,  3.03it/s]
726.408964404 m 876.263863518 m 801.336413961 m
Image shape: (720, 1280, 3)
 58%|█████▊    | 726/1261 [04:05<02:57,  3.01it/s]
672.67723675 m 562.718307243 m 617.697771997 m
Image shape: (720, 1280, 3)
 58%|█████▊    | 727/1261 [04:05<02:56,  3.03it/s]
685.606841732 m 483.581191487 m 584.59401661 m
Image shape: (720, 1280, 3)
 58%|█████▊    | 728/1261 [04:06<02:55,  3.03it/s]
606.888247072 m 352.001887125 m 479.445067099 m
Image shape: (720, 1280, 3)
 58%|█████▊    | 729/1261 [04:06<02:55,  3.03it/s]
590.665002946 m 352.017203099 m 471.341103022 m
Image shape: (720, 1280, 3)
 58%|█████▊    | 730/1261 [04:06<02:56,  3.02it/s]
592.098367508 m 401.831225278 m 496.964796393 m
Image shape: (720, 1280, 3)
 58%|█████▊    | 731/1261 [04:07<02:55,  3.02it/s]
557.049795618 m 395.423571845 m 476.236683732 m
Image shape: (720, 1280, 3)
 58%|█████▊    | 732/1261 [04:07<02:54,  3.04it/s]
560.017832824 m 638.006983461 m 599.012408142 m
Image shape: (720, 1280, 3)
 58%|█████▊    | 733/1261 [04:07<02:54,  3.03it/s]
517.514265447 m 407.460714235 m 462.487489841 m
Image shape: (720, 1280, 3)
 58%|█████▊    | 734/1261 [04:08<02:53,  3.03it/s]
500.906779742 m 598.173598967 m 549.540189355 m
Image shape: (720, 1280, 3)
 58%|█████▊    | 735/1261 [04:08<02:53,  3.03it/s]
466.222615041 m 1228.09792861 m 847.160271828 m
Image shape: (720, 1280, 3)
 58%|█████▊    | 736/1261 [04:08<02:52,  3.03it/s]
474.355308506 m 992.276468968 m 733.315888737 m
Image shape: (720, 1280, 3)
 58%|█████▊    | 737/1261 [04:09<02:52,  3.04it/s]
489.677659104 m 750.282270179 m 619.979964642 m
Image shape: (720, 1280, 3)
 59%|█████▊    | 738/1261 [04:09<02:52,  3.04it/s]
474.525827919 m 518.512845818 m 496.519336869 m
Image shape: (720, 1280, 3)
 59%|█████▊    | 739/1261 [04:09<02:51,  3.04it/s]
518.054024378 m 395.615210174 m 456.834617276 m
Image shape: (720, 1280, 3)
 59%|█████▊    | 740/1261 [04:10<02:51,  3.03it/s]
525.111390802 m 313.475564288 m 419.293477545 m
Image shape: (720, 1280, 3)
 59%|█████▉    | 741/1261 [04:10<02:52,  3.02it/s]
571.279417644 m 347.772499259 m 459.525958452 m
Image shape: (720, 1280, 3)
 59%|█████▉    | 742/1261 [04:10<02:51,  3.03it/s]
619.149515628 m 381.006967594 m 500.078241611 m
Image shape: (720, 1280, 3)
 59%|█████▉    | 743/1261 [04:11<02:51,  3.03it/s]
597.663358344 m 363.650796375 m 480.65707736 m
Image shape: (720, 1280, 3)
 59%|█████▉    | 744/1261 [04:11<02:51,  3.02it/s]
572.257635885 m 346.215533728 m 459.236584807 m
Image shape: (720, 1280, 3)
 59%|█████▉    | 745/1261 [04:11<02:51,  3.01it/s]
568.930981494 m 369.830917128 m 469.380949311 m
Image shape: (720, 1280, 3)
 59%|█████▉    | 746/1261 [04:12<02:51,  3.00it/s]
559.442467718 m 479.274854074 m 519.358660896 m
Image shape: (720, 1280, 3)
 59%|█████▉    | 747/1261 [04:12<02:51,  3.00it/s]
612.314023976 m 706.309134478 m 659.311579227 m
Image shape: (720, 1280, 3)
 59%|█████▉    | 748/1261 [04:12<02:51,  2.99it/s]
564.626538965 m 593.662347493 m 579.144443229 m
Image shape: (720, 1280, 3)
 59%|█████▉    | 749/1261 [04:13<02:50,  3.01it/s]
559.344346887 m 584.074705669 m 571.709526278 m
Image shape: (720, 1280, 3)
 59%|█████▉    | 750/1261 [04:13<02:49,  3.01it/s]
540.519099583 m 402.874241398 m 471.696670491 m
Image shape: (720, 1280, 3)
 60%|█████▉    | 751/1261 [04:13<02:53,  2.94it/s]
542.694170106 m 337.623657485 m 440.158913796 m
Image shape: (720, 1280, 3)
 60%|█████▉    | 752/1261 [04:14<02:55,  2.90it/s]
583.554031681 m 258.899142436 m 421.226587058 m
Image shape: (720, 1280, 3)
 60%|█████▉    | 753/1261 [04:14<02:54,  2.91it/s]
578.082711556 m 259.600722268 m 418.841716912 m
Image shape: (720, 1280, 3)
 60%|█████▉    | 754/1261 [04:14<02:51,  2.95it/s]
615.609193942 m 304.182901089 m 459.896047516 m
Image shape: (720, 1280, 3)
 60%|█████▉    | 755/1261 [04:15<02:49,  2.99it/s]
605.880982396 m 296.186987975 m 451.033985185 m
Image shape: (720, 1280, 3)
 60%|█████▉    | 756/1261 [04:15<02:47,  3.01it/s]
627.590553627 m 296.205495942 m 461.898024784 m
Image shape: (720, 1280, 3)
 60%|██████    | 757/1261 [04:15<02:47,  3.02it/s]
646.245231218 m 364.402355866 m 505.323793542 m
Image shape: (720, 1280, 3)
 60%|██████    | 758/1261 [04:16<02:45,  3.04it/s]
710.937023377 m 379.460157385 m 545.198590381 m
Image shape: (720, 1280, 3)
 60%|██████    | 759/1261 [04:16<02:44,  3.05it/s]
637.963980601 m 550.280040119 m 594.12201036 m
Image shape: (720, 1280, 3)
 60%|██████    | 760/1261 [04:16<02:44,  3.05it/s]
648.745365897 m 695.499563978 m 672.122464938 m
Image shape: (720, 1280, 3)
 60%|██████    | 761/1261 [04:17<02:44,  3.05it/s]
551.155919839 m 691.641731587 m 621.398825713 m
Image shape: (720, 1280, 3)
 60%|██████    | 762/1261 [04:17<02:44,  3.03it/s]
556.855040344 m 418.56070244 m 487.707871392 m
Image shape: (720, 1280, 3)
 61%|██████    | 763/1261 [04:17<02:44,  3.03it/s]
501.878470255 m 359.464791884 m 430.67163107 m
Image shape: (720, 1280, 3)
 61%|██████    | 764/1261 [04:18<02:44,  3.03it/s]
513.231284741 m 278.054057478 m 395.642671109 m
Image shape: (720, 1280, 3)
 61%|██████    | 765/1261 [04:18<02:43,  3.04it/s]
511.592514953 m 279.550488059 m 395.571501506 m
Image shape: (720, 1280, 3)
 61%|██████    | 766/1261 [04:18<02:42,  3.04it/s]
500.818546584 m 300.49322615 m 400.655886367 m
Image shape: (720, 1280, 3)
 61%|██████    | 767/1261 [04:19<02:45,  2.98it/s]
507.156319952 m 327.965715884 m 417.561017918 m
Image shape: (720, 1280, 3)
 61%|██████    | 768/1261 [04:19<02:45,  2.98it/s]
475.045968715 m 368.508572158 m 421.777270437 m
Image shape: (720, 1280, 3)
 61%|██████    | 769/1261 [04:19<02:43,  3.00it/s]
479.701658259 m 349.708375891 m 414.705017075 m
Image shape: (720, 1280, 3)
 61%|██████    | 770/1261 [04:20<02:43,  3.01it/s]
461.844227087 m 584.201176792 m 523.022701939 m
Image shape: (720, 1280, 3)
 61%|██████    | 771/1261 [04:20<02:42,  3.02it/s]
468.333409065 m 793.962524532 m 631.147966798 m
Image shape: (720, 1280, 3)
 61%|██████    | 772/1261 [04:20<02:41,  3.03it/s]
522.219710443 m 732.245461422 m 627.232585933 m
Image shape: (720, 1280, 3)
 61%|██████▏   | 773/1261 [04:21<02:40,  3.04it/s]
543.781897808 m 876.328777534 m 710.055337671 m
Image shape: (720, 1280, 3)
 61%|██████▏   | 774/1261 [04:21<02:39,  3.04it/s]
493.038833104 m 493.336149136 m 493.18749112 m
Image shape: (720, 1280, 3)
 61%|██████▏   | 775/1261 [04:21<02:40,  3.03it/s]
512.231830846 m 406.820187585 m 459.526009215 m
Image shape: (720, 1280, 3)
 62%|██████▏   | 776/1261 [04:22<02:40,  3.03it/s]
538.719452281 m 310.248078512 m 424.483765396 m
Image shape: (720, 1280, 3)
 62%|██████▏   | 777/1261 [04:22<02:40,  3.02it/s]
552.734280163 m 305.074303368 m 428.904291765 m
Image shape: (720, 1280, 3)
 62%|██████▏   | 778/1261 [04:22<02:39,  3.03it/s]
576.41581696 m 378.46245949 m 477.439138225 m
Image shape: (720, 1280, 3)
 62%|██████▏   | 779/1261 [04:23<02:39,  3.03it/s]
563.196440229 m 520.869399915 m 542.032920072 m
Image shape: (720, 1280, 3)
 62%|██████▏   | 780/1261 [04:23<02:38,  3.04it/s]
581.150354589 m 349.960262561 m 465.555308575 m
Image shape: (720, 1280, 3)
 62%|██████▏   | 781/1261 [04:23<02:38,  3.04it/s]
584.525565535 m 370.359722458 m 477.442643996 m
Image shape: (720, 1280, 3)
 62%|██████▏   | 782/1261 [04:24<02:37,  3.04it/s]
678.240841534 m 403.356298499 m 540.798570017 m
Image shape: (720, 1280, 3)
 62%|██████▏   | 783/1261 [04:24<02:37,  3.04it/s]
647.552130696 m 513.57590333 m 580.564017013 m
Image shape: (720, 1280, 3)
 62%|██████▏   | 784/1261 [04:24<02:37,  3.04it/s]
704.11499979 m 542.580955037 m 623.347977413 m
Image shape: (720, 1280, 3)
 62%|██████▏   | 785/1261 [04:25<02:37,  3.03it/s]
691.035756615 m 656.099109382 m 673.567432998 m
Image shape: (720, 1280, 3)
 62%|██████▏   | 786/1261 [04:25<02:36,  3.03it/s]
681.130059649 m 484.823974059 m 582.977016854 m
Image shape: (720, 1280, 3)
 62%|██████▏   | 787/1261 [04:25<02:36,  3.02it/s]
625.376237142 m 448.420726256 m 536.898481699 m
Image shape: (720, 1280, 3)
 62%|██████▏   | 788/1261 [04:26<02:36,  3.03it/s]
641.737864381 m 302.88237925 m 472.310121816 m
Image shape: (720, 1280, 3)
 63%|██████▎   | 789/1261 [04:26<02:36,  3.02it/s]
654.910908355 m 437.80067103 m 546.355789692 m
Image shape: (720, 1280, 3)
 63%|██████▎   | 790/1261 [04:26<02:35,  3.02it/s]
791.933356587 m 302.437344986 m 547.185350787 m
Image shape: (720, 1280, 3)
 63%|██████▎   | 791/1261 [04:27<02:35,  3.02it/s]
732.335234595 m 495.605947084 m 613.97059084 m
Image shape: (720, 1280, 3)
 63%|██████▎   | 792/1261 [04:27<02:35,  3.01it/s]
807.669282101 m 323.185201977 m 565.427242039 m
Image shape: (720, 1280, 3)
 63%|██████▎   | 793/1261 [04:27<02:36,  2.99it/s]
893.081851336 m 317.487668856 m 605.284760096 m
Image shape: (720, 1280, 3)
 63%|██████▎   | 794/1261 [04:28<02:36,  2.98it/s]
927.280543674 m 487.025928891 m 707.153236282 m
Image shape: (720, 1280, 3)
 63%|██████▎   | 795/1261 [04:28<02:35,  2.99it/s]
966.694046573 m 607.863232354 m 787.278639463 m
Image shape: (720, 1280, 3)
 63%|██████▎   | 796/1261 [04:28<02:35,  2.99it/s]
885.032674443 m 755.488159803 m 820.260417123 m
Image shape: (720, 1280, 3)
 63%|██████▎   | 797/1261 [04:29<02:33,  3.02it/s]
905.952467916 m 865.300837142 m 885.626652529 m
Image shape: (720, 1280, 3)
 63%|██████▎   | 798/1261 [04:29<02:32,  3.03it/s]
855.448645936 m 701.078495211 m 778.263570574 m
Image shape: (720, 1280, 3)
 63%|██████▎   | 799/1261 [04:29<02:32,  3.04it/s]
923.104556257 m 623.586302844 m 773.34542955 m
Image shape: (720, 1280, 3)
 63%|██████▎   | 800/1261 [04:30<02:32,  3.03it/s]
1021.51552232 m 575.0005453 m 798.258033809 m
Image shape: (720, 1280, 3)
 64%|██████▎   | 801/1261 [04:30<02:32,  3.02it/s]
1192.58779479 m 580.439157028 m 886.51347591 m
Image shape: (720, 1280, 3)
 64%|██████▎   | 802/1261 [04:30<02:31,  3.03it/s]
1230.34209918 m 402.347853311 m 816.344976247 m
Image shape: (720, 1280, 3)
 64%|██████▎   | 803/1261 [04:31<02:31,  3.03it/s]
1382.66463952 m 724.210715498 m 1053.43767751 m
Image shape: (720, 1280, 3)
 64%|██████▍   | 804/1261 [04:31<02:30,  3.04it/s]
1027.93752968 m 367.002311587 m 697.469920634 m
Image shape: (720, 1280, 3)
 64%|██████▍   | 805/1261 [04:31<02:30,  3.04it/s]
894.997716828 m 665.714317747 m 780.356017288 m
Image shape: (720, 1280, 3)
 64%|██████▍   | 806/1261 [04:32<02:30,  3.02it/s]
969.462472473 m 841.815838135 m 905.639155304 m
Image shape: (720, 1280, 3)
 64%|██████▍   | 807/1261 [04:32<02:30,  3.01it/s]
883.418096484 m 1064.37785813 m 973.897977307 m
Image shape: (720, 1280, 3)
 64%|██████▍   | 808/1261 [04:32<02:30,  3.01it/s]
775.288589013 m 1192.88170057 m 984.08514479 m
Image shape: (720, 1280, 3)
 64%|██████▍   | 809/1261 [04:33<02:29,  3.02it/s]
768.753865473 m 967.04614095 m 867.900003211 m
Image shape: (720, 1280, 3)
 64%|██████▍   | 810/1261 [04:33<02:28,  3.04it/s]
758.080880548 m 924.174483135 m 841.127681842 m
Image shape: (720, 1280, 3)
 64%|██████▍   | 811/1261 [04:33<02:28,  3.03it/s]
644.994553363 m 521.166061826 m 583.080307594 m
Image shape: (720, 1280, 3)
 64%|██████▍   | 812/1261 [04:34<02:28,  3.02it/s]
676.933312246 m 547.576258938 m 612.254785592 m
Image shape: (720, 1280, 3)
 64%|██████▍   | 813/1261 [04:34<02:29,  3.01it/s]
647.860044825 m 600.25791993 m 624.058982378 m
Image shape: (720, 1280, 3)
 65%|██████▍   | 814/1261 [04:34<02:27,  3.02it/s]
708.87687365 m 425.270874085 m 567.073873867 m
Image shape: (720, 1280, 3)
 65%|██████▍   | 815/1261 [04:35<02:27,  3.02it/s]
655.41732351 m 404.400320339 m 529.908821925 m
Image shape: (720, 1280, 3)
 65%|██████▍   | 816/1261 [04:35<02:27,  3.02it/s]
564.087633942 m 310.948864399 m 437.51824917 m
Image shape: (720, 1280, 3)
 65%|██████▍   | 817/1261 [04:35<02:26,  3.03it/s]
564.539447901 m 368.60346274 m 466.57145532 m
Image shape: (720, 1280, 3)
 65%|██████▍   | 818/1261 [04:36<02:26,  3.02it/s]
559.930814781 m 442.133892375 m 501.032353578 m
Image shape: (720, 1280, 3)
 65%|██████▍   | 819/1261 [04:36<02:26,  3.02it/s]
595.985633221 m 470.666164621 m 533.325898921 m
Image shape: (720, 1280, 3)
 65%|██████▌   | 820/1261 [04:36<02:26,  3.02it/s]
668.015738386 m 487.020042305 m 577.517890345 m
Image shape: (720, 1280, 3)
 65%|██████▌   | 821/1261 [04:37<02:24,  3.04it/s]
747.105837553 m 477.891973965 m 612.498905759 m
Image shape: (720, 1280, 3)
 65%|██████▌   | 822/1261 [04:37<02:25,  3.03it/s]
731.592604984 m 454.657696334 m 593.125150659 m
Image shape: (720, 1280, 3)
 65%|██████▌   | 823/1261 [04:37<02:24,  3.03it/s]
746.458743003 m 404.883390911 m 575.671066957 m
Image shape: (720, 1280, 3)
 65%|██████▌   | 824/1261 [04:38<02:23,  3.04it/s]
773.806172479 m 376.083882655 m 574.945027567 m
Image shape: (720, 1280, 3)
 65%|██████▌   | 825/1261 [04:38<02:23,  3.03it/s]
811.621137374 m 391.014380031 m 601.317758702 m
Image shape: (720, 1280, 3)
 66%|██████▌   | 826/1261 [04:38<02:23,  3.03it/s]
728.228202252 m 400.185296264 m 564.206749258 m
Image shape: (720, 1280, 3)
 66%|██████▌   | 827/1261 [04:39<02:23,  3.03it/s]
693.501722073 m 404.995435022 m 549.248578547 m
Image shape: (720, 1280, 3)
 66%|██████▌   | 828/1261 [04:39<02:22,  3.04it/s]
685.017916226 m 244.359935039 m 464.688925632 m
Image shape: (720, 1280, 3)
 66%|██████▌   | 829/1261 [04:39<02:26,  2.95it/s]
735.051011677 m 236.449465305 m 485.750238491 m
Image shape: (720, 1280, 3)
 66%|██████▌   | 830/1261 [04:40<02:27,  2.91it/s]
835.235053065 m 311.689030949 m 573.462042007 m
Image shape: (720, 1280, 3)
 66%|██████▌   | 831/1261 [04:40<02:30,  2.87it/s]
782.64760514 m 461.990303562 m 622.318954351 m
Image shape: (720, 1280, 3)
 66%|██████▌   | 832/1261 [04:40<02:28,  2.90it/s]
764.741730016 m 476.126051857 m 620.433890937 m
Image shape: (720, 1280, 3)
 66%|██████▌   | 833/1261 [04:41<02:26,  2.93it/s]
723.244754712 m 411.641346118 m 567.443050415 m
Image shape: (720, 1280, 3)
 66%|██████▌   | 834/1261 [04:41<02:25,  2.94it/s]
795.184890769 m 384.244752237 m 589.714821503 m
Image shape: (720, 1280, 3)
 66%|██████▌   | 835/1261 [04:41<02:24,  2.95it/s]
648.999677404 m 276.883787165 m 462.941732284 m
Image shape: (720, 1280, 3)
 66%|██████▋   | 836/1261 [04:42<02:23,  2.96it/s]
629.880623441 m 275.520831396 m 452.700727419 m
Image shape: (720, 1280, 3)
 66%|██████▋   | 837/1261 [04:42<02:23,  2.96it/s]
612.375721434 m 280.336762008 m 446.356241721 m
Image shape: (720, 1280, 3)
 66%|██████▋   | 838/1261 [04:42<02:21,  2.98it/s]
593.585038646 m 281.916694348 m 437.750866497 m
Image shape: (720, 1280, 3)
 67%|██████▋   | 839/1261 [04:43<02:20,  3.01it/s]
575.964046958 m 267.419380208 m 421.691713583 m
Image shape: (720, 1280, 3)
 67%|██████▋   | 840/1261 [04:43<02:19,  3.02it/s]
635.672492399 m 233.930168573 m 434.801330486 m
Image shape: (720, 1280, 3)
 67%|██████▋   | 841/1261 [04:43<02:19,  3.01it/s]
662.429783766 m 227.347135313 m 444.88845954 m
Image shape: (720, 1280, 3)
 67%|██████▋   | 842/1261 [04:44<02:19,  3.00it/s]
669.548865023 m 253.304781759 m 461.426823391 m
Image shape: (720, 1280, 3)
 67%|██████▋   | 843/1261 [04:44<02:19,  3.00it/s]
632.135189084 m 256.276644899 m 444.205916991 m
Image shape: (720, 1280, 3)
 67%|██████▋   | 844/1261 [04:44<02:18,  3.02it/s]
695.756326503 m 364.940099818 m 530.348213161 m
Image shape: (720, 1280, 3)
 67%|██████▋   | 845/1261 [04:45<02:18,  3.01it/s]
679.092660724 m 342.636602295 m 510.864631509 m
Image shape: (720, 1280, 3)
 67%|██████▋   | 846/1261 [04:45<02:18,  3.00it/s]
653.412680027 m 346.231249911 m 499.821964969 m
Image shape: (720, 1280, 3)
 67%|██████▋   | 847/1261 [04:45<02:17,  3.00it/s]
636.369516218 m 301.286076126 m 468.827796172 m
Image shape: (720, 1280, 3)
 67%|██████▋   | 848/1261 [04:46<02:17,  3.00it/s]
568.401696062 m 297.142868819 m 432.77228244 m
Image shape: (720, 1280, 3)
 67%|██████▋   | 849/1261 [04:46<02:16,  3.01it/s]
673.615306466 m 283.081274 m 478.348290233 m
Image shape: (720, 1280, 3)
 67%|██████▋   | 850/1261 [04:46<02:17,  3.00it/s]
647.139909455 m 291.976616229 m 469.558262842 m
Image shape: (720, 1280, 3)
 67%|██████▋   | 851/1261 [04:47<02:17,  2.99it/s]
730.977288035 m 259.623842747 m 495.300565391 m
Image shape: (720, 1280, 3)
 68%|██████▊   | 852/1261 [04:47<02:15,  3.01it/s]
762.628730409 m 248.405024408 m 505.516877409 m
Image shape: (720, 1280, 3)
 68%|██████▊   | 853/1261 [04:47<02:14,  3.03it/s]
748.526904817 m 255.432450517 m 501.979677667 m
Image shape: (720, 1280, 3)
 68%|██████▊   | 854/1261 [04:48<02:14,  3.03it/s]
882.664522532 m 244.234914805 m 563.449718669 m
Image shape: (720, 1280, 3)
 68%|██████▊   | 855/1261 [04:48<02:14,  3.02it/s]
1020.82029065 m 380.701264907 m 700.76077778 m
Image shape: (720, 1280, 3)
 68%|██████▊   | 856/1261 [04:48<02:14,  3.01it/s]
1161.93367992 m 391.338815852 m 776.636247885 m
Image shape: (720, 1280, 3)
 68%|██████▊   | 857/1261 [04:49<02:15,  2.99it/s]
1382.45655301 m 387.185768681 m 884.821160844 m
Image shape: (720, 1280, 3)
 68%|██████▊   | 858/1261 [04:49<02:13,  3.02it/s]
908.923751555 m 295.823498511 m 602.373625033 m
Image shape: (720, 1280, 3)
 68%|██████▊   | 859/1261 [04:49<02:13,  3.02it/s]
1055.25444203 m 270.671474001 m 662.962958017 m
Image shape: (720, 1280, 3)
 68%|██████▊   | 860/1261 [04:50<02:12,  3.02it/s]
793.71520669 m 282.219563467 m 537.967385079 m
Image shape: (720, 1280, 3)
 68%|██████▊   | 861/1261 [04:50<02:12,  3.01it/s]
817.716578011 m 265.183978176 m 541.450278094 m
Image shape: (720, 1280, 3)
 68%|██████▊   | 862/1261 [04:50<02:12,  3.02it/s]
833.282381956 m 303.510670369 m 568.396526163 m
Image shape: (720, 1280, 3)
 68%|██████▊   | 863/1261 [04:51<02:11,  3.03it/s]
912.294083079 m 248.42370415 m 580.358893614 m
Image shape: (720, 1280, 3)
 69%|██████▊   | 864/1261 [04:51<02:11,  3.01it/s]
1064.5790615 m 245.395771533 m 654.987416515 m
Image shape: (720, 1280, 3)
 69%|██████▊   | 865/1261 [04:51<02:11,  3.01it/s]
1042.77471628 m 265.924592165 m 654.349654221 m
Image shape: (720, 1280, 3)
 69%|██████▊   | 866/1261 [04:52<02:11,  3.00it/s]
1334.42856654 m 314.391009947 m 824.409788243 m
Image shape: (720, 1280, 3)
 69%|██████▉   | 867/1261 [04:52<02:10,  3.01it/s]
1652.73718654 m 368.128287124 m 1010.43273683 m
Image shape: (720, 1280, 3)
 69%|██████▉   | 868/1261 [04:52<02:10,  3.02it/s]
1541.88455356 m 585.145716669 m 1063.51513512 m
Image shape: (720, 1280, 3)
 69%|██████▉   | 869/1261 [04:53<02:09,  3.03it/s]
1413.96248884 m 353.746643582 m 883.854566209 m
Image shape: (720, 1280, 3)
 69%|██████▉   | 870/1261 [04:53<02:08,  3.04it/s]
1562.05694374 m 297.955744071 m 930.006343905 m
Image shape: (720, 1280, 3)
 69%|██████▉   | 871/1261 [04:53<02:11,  2.98it/s]
1114.52248693 m 276.94807527 m 695.7352811 m
Image shape: (720, 1280, 3)
 69%|██████▉   | 872/1261 [04:54<02:10,  2.97it/s]
934.037892839 m 306.658190818 m 620.348041828 m
Image shape: (720, 1280, 3)
 69%|██████▉   | 873/1261 [04:54<02:10,  2.97it/s]
716.249819322 m 328.818657201 m 522.534238261 m
Image shape: (720, 1280, 3)
 69%|██████▉   | 874/1261 [04:54<02:10,  2.95it/s]
789.431012177 m 344.516183879 m 566.973598028 m
Image shape: (720, 1280, 3)
 69%|██████▉   | 875/1261 [04:55<02:11,  2.94it/s]
872.559472566 m 305.674621133 m 589.117046849 m
Image shape: (720, 1280, 3)
 69%|██████▉   | 876/1261 [04:55<02:09,  2.96it/s]
922.115447906 m 344.821901851 m 633.468674878 m
Image shape: (720, 1280, 3)
 70%|██████▉   | 877/1261 [04:55<02:09,  2.96it/s]
965.753042666 m 414.972231141 m 690.362636903 m
Image shape: (720, 1280, 3)
 70%|██████▉   | 878/1261 [04:56<02:08,  2.98it/s]
783.700447056 m 523.100921305 m 653.40068418 m
Image shape: (720, 1280, 3)
 70%|██████▉   | 879/1261 [04:56<02:07,  2.99it/s]
661.652243138 m 530.669486997 m 596.160865067 m
Image shape: (720, 1280, 3)
 70%|██████▉   | 880/1261 [04:56<02:06,  3.02it/s]
602.193557706 m 871.102224437 m 736.647891071 m
Image shape: (720, 1280, 3)
 70%|██████▉   | 881/1261 [04:57<02:06,  3.01it/s]
561.120469415 m 327.429043451 m 444.274756433 m
Image shape: (720, 1280, 3)
 70%|██████▉   | 882/1261 [04:57<02:05,  3.02it/s]
586.206299718 m 317.304235058 m 451.755267388 m
Image shape: (720, 1280, 3)
 70%|███████   | 883/1261 [04:57<02:05,  3.02it/s]
601.378019376 m 305.711366952 m 453.544693164 m
Image shape: (720, 1280, 3)
 70%|███████   | 884/1261 [04:58<02:04,  3.02it/s]
677.803565044 m 331.93926686 m 504.871415952 m
Image shape: (720, 1280, 3)
 70%|███████   | 885/1261 [04:58<02:04,  3.02it/s]
726.2802998 m 397.543135884 m 561.911717842 m
Image shape: (720, 1280, 3)
 70%|███████   | 886/1261 [04:58<02:04,  3.02it/s]
759.364873344 m 315.043152745 m 537.204013044 m
Image shape: (720, 1280, 3)
 70%|███████   | 887/1261 [04:59<02:05,  2.99it/s]
861.32863775 m 314.483920144 m 587.906278947 m
Image shape: (720, 1280, 3)
 70%|███████   | 888/1261 [04:59<02:04,  2.99it/s]
833.052072015 m 360.723049916 m 596.887560965 m
Image shape: (720, 1280, 3)
 70%|███████   | 889/1261 [04:59<02:03,  3.00it/s]
1194.12851237 m 415.617189293 m 804.872850834 m
Image shape: (720, 1280, 3)
 71%|███████   | 890/1261 [05:00<02:04,  2.99it/s]
1231.23138322 m 435.57896038 m 833.4051718 m
Image shape: (720, 1280, 3)
 71%|███████   | 891/1261 [05:00<02:03,  3.00it/s]
1828.92891595 m 410.109909672 m 1119.51941281 m
Image shape: (720, 1280, 3)
 71%|███████   | 892/1261 [05:00<02:03,  2.99it/s]
2050.69158187 m 276.511496819 m 1163.60153934 m
Image shape: (720, 1280, 3)
 71%|███████   | 893/1261 [05:01<02:02,  2.99it/s]
1947.33130401 m 374.107733825 m 1160.71951892 m
Image shape: (720, 1280, 3)
 71%|███████   | 894/1261 [05:01<02:02,  2.98it/s]
1994.0967825 m 327.256863909 m 1160.67682321 m
Image shape: (720, 1280, 3)
 71%|███████   | 895/1261 [05:01<02:02,  2.99it/s]
1787.01899664 m 327.78974997 m 1057.4043733 m
Image shape: (720, 1280, 3)
 71%|███████   | 896/1261 [05:02<02:03,  2.95it/s]
1230.5833389 m 338.03369998 m 784.30851944 m
Image shape: (720, 1280, 3)
 71%|███████   | 897/1261 [05:02<02:03,  2.95it/s]
1114.24325596 m 344.600047358 m 729.421651659 m
Image shape: (720, 1280, 3)
 71%|███████   | 898/1261 [05:02<02:02,  2.97it/s]
928.139616115 m 312.147750249 m 620.143683182 m
Image shape: (720, 1280, 3)
 71%|███████▏  | 899/1261 [05:03<02:03,  2.93it/s]
972.444981078 m 373.496195777 m 672.970588428 m
Image shape: (720, 1280, 3)
 71%|███████▏  | 900/1261 [05:03<02:01,  2.96it/s]
1251.48324435 m 352.505624773 m 801.994434562 m
Image shape: (720, 1280, 3)
 71%|███████▏  | 901/1261 [05:03<02:00,  2.98it/s]
1092.93674372 m 344.143555385 m 718.540149554 m
Image shape: (720, 1280, 3)
 72%|███████▏  | 902/1261 [05:04<01:59,  3.01it/s]
1214.02538126 m 421.805315737 m 817.915348499 m
Image shape: (720, 1280, 3)
 72%|███████▏  | 903/1261 [05:04<01:59,  3.01it/s]
1073.64495847 m 567.794646191 m 820.719802331 m
Image shape: (720, 1280, 3)
 72%|███████▏  | 904/1261 [05:04<01:58,  3.02it/s]
1178.21985597 m 401.945353926 m 790.08260495 m
Image shape: (720, 1280, 3)
 72%|███████▏  | 905/1261 [05:05<01:57,  3.02it/s]
1194.73530202 m 378.348313896 m 786.541807959 m
Image shape: (720, 1280, 3)
 72%|███████▏  | 906/1261 [05:05<01:59,  2.98it/s]
1024.39216543 m 298.67387116 m 661.533018296 m
Image shape: (720, 1280, 3)
 72%|███████▏  | 907/1261 [05:05<02:00,  2.94it/s]
944.439390103 m 318.398762357 m 631.41907623 m
Image shape: (720, 1280, 3)
 72%|███████▏  | 908/1261 [05:06<02:01,  2.90it/s]
886.999355656 m 301.428313685 m 594.21383467 m
Image shape: (720, 1280, 3)
 72%|███████▏  | 909/1261 [05:06<02:00,  2.92it/s]
878.750392735 m 338.329558278 m 608.539975506 m
Image shape: (720, 1280, 3)
 72%|███████▏  | 910/1261 [05:06<01:58,  2.96it/s]
1021.31155732 m 264.366709659 m 642.83913349 m
Image shape: (720, 1280, 3)
 72%|███████▏  | 911/1261 [05:07<01:57,  2.97it/s]
885.655062986 m 271.386402635 m 578.520732811 m
Image shape: (720, 1280, 3)
 72%|███████▏  | 912/1261 [05:07<01:57,  2.97it/s]
887.499184595 m 283.069239119 m 585.284211857 m
Image shape: (720, 1280, 3)
 72%|███████▏  | 913/1261 [05:07<01:56,  3.00it/s]
821.215651889 m 300.365127238 m 560.790389564 m
Image shape: (720, 1280, 3)
 72%|███████▏  | 914/1261 [05:08<01:56,  2.99it/s]
705.50427406 m 376.31669009 m 540.910482075 m
Image shape: (720, 1280, 3)
 73%|███████▎  | 915/1261 [05:08<01:55,  2.99it/s]
612.608173177 m 498.222414147 m 555.415293662 m
Image shape: (720, 1280, 3)
 73%|███████▎  | 916/1261 [05:08<01:55,  2.99it/s]
595.003237748 m 345.891467568 m 470.447352658 m
Image shape: (720, 1280, 3)
 73%|███████▎  | 917/1261 [05:09<01:54,  3.00it/s]
524.285601046 m 350.489641033 m 437.387621039 m
Image shape: (720, 1280, 3)
 73%|███████▎  | 918/1261 [05:09<01:54,  2.99it/s]
628.667168682 m 332.677609815 m 480.672389248 m
Image shape: (720, 1280, 3)
 73%|███████▎  | 919/1261 [05:09<01:53,  3.01it/s]
521.342339943 m 331.670915613 m 426.506627778 m
Image shape: (720, 1280, 3)
 73%|███████▎  | 920/1261 [05:10<01:52,  3.04it/s]
467.148415926 m 302.359801501 m 384.754108714 m
Image shape: (720, 1280, 3)
 73%|███████▎  | 921/1261 [05:10<01:51,  3.04it/s]
484.601977064 m 363.641256473 m 424.121616768 m
Image shape: (720, 1280, 3)
 73%|███████▎  | 922/1261 [05:10<01:51,  3.03it/s]
546.084897389 m 289.400407831 m 417.74265261 m
Image shape: (720, 1280, 3)
 73%|███████▎  | 923/1261 [05:11<01:51,  3.04it/s]
629.222372715 m 305.680103852 m 467.451238283 m
Image shape: (720, 1280, 3)
 73%|███████▎  | 924/1261 [05:11<01:50,  3.04it/s]
753.556602361 m 318.416470962 m 535.986536662 m
Image shape: (720, 1280, 3)
 73%|███████▎  | 925/1261 [05:11<01:50,  3.05it/s]
629.867866472 m 408.775617517 m 519.321741995 m
Image shape: (720, 1280, 3)
 73%|███████▎  | 926/1261 [05:12<01:50,  3.04it/s]
731.19345336 m 943.961371574 m 837.577412467 m
Image shape: (720, 1280, 3)
 74%|███████▎  | 927/1261 [05:12<01:50,  3.04it/s]
863.666086145 m 743.112719156 m 803.389402651 m
Image shape: (720, 1280, 3)
 74%|███████▎  | 928/1261 [05:12<01:49,  3.04it/s]
896.266269584 m 459.146881478 m 677.706575531 m
Image shape: (720, 1280, 3)
 74%|███████▎  | 929/1261 [05:13<01:49,  3.04it/s]
1048.72912509 m 369.989519215 m 709.359322151 m
Image shape: (720, 1280, 3)
 74%|███████▍  | 930/1261 [05:13<01:49,  3.03it/s]
1236.1717534 m 369.08103149 m 802.626392443 m
Image shape: (720, 1280, 3)
 74%|███████▍  | 931/1261 [05:13<01:48,  3.03it/s]
879.105068212 m 367.127746789 m 623.116407501 m
Image shape: (720, 1280, 3)
 74%|███████▍  | 932/1261 [05:14<01:48,  3.02it/s]
958.604304986 m 348.317268405 m 653.460786696 m
Image shape: (720, 1280, 3)
 74%|███████▍  | 933/1261 [05:14<01:48,  3.03it/s]
992.574451097 m 368.319154827 m 680.446802962 m
Image shape: (720, 1280, 3)
 74%|███████▍  | 934/1261 [05:14<01:47,  3.04it/s]
914.871096405 m 287.175933377 m 601.023514891 m
Image shape: (720, 1280, 3)
 74%|███████▍  | 935/1261 [05:15<01:47,  3.02it/s]
1038.41198183 m 578.911264034 m 808.66162293 m
Image shape: (720, 1280, 3)
 74%|███████▍  | 936/1261 [05:15<01:48,  3.01it/s]
986.217373945 m 324.707870844 m 655.462622395 m
Image shape: (720, 1280, 3)
 74%|███████▍  | 937/1261 [05:15<01:48,  2.98it/s]
979.629522695 m 413.160861918 m 696.395192307 m
Image shape: (720, 1280, 3)
 74%|███████▍  | 938/1261 [05:16<01:49,  2.94it/s]
867.021990182 m 630.928095482 m 748.975042832 m
Image shape: (720, 1280, 3)
 74%|███████▍  | 939/1261 [05:16<01:50,  2.91it/s]
691.706473446 m 373.39910096 m 532.552787203 m
Image shape: (720, 1280, 3)
 75%|███████▍  | 940/1261 [05:16<01:49,  2.92it/s]
602.16844881 m 358.842018258 m 480.505233534 m
Image shape: (720, 1280, 3)
 75%|███████▍  | 941/1261 [05:17<01:48,  2.95it/s]
621.877478817 m 252.402805189 m 437.140142003 m
Image shape: (720, 1280, 3)
 75%|███████▍  | 942/1261 [05:17<01:47,  2.97it/s]
582.780841021 m 270.269217687 m 426.525029354 m
Image shape: (720, 1280, 3)
 75%|███████▍  | 943/1261 [05:17<01:46,  2.98it/s]
674.761292644 m 259.192022475 m 466.97665756 m
Image shape: (720, 1280, 3)
 75%|███████▍  | 944/1261 [05:18<01:46,  2.99it/s]
617.725882491 m 269.446349683 m 443.586116087 m
Image shape: (720, 1280, 3)
 75%|███████▍  | 945/1261 [05:18<01:44,  3.02it/s]
584.317857411 m 287.308625929 m 435.81324167 m
Image shape: (720, 1280, 3)
 75%|███████▌  | 946/1261 [05:18<01:45,  2.99it/s]
661.015099337 m 247.698852211 m 454.356975774 m
Image shape: (720, 1280, 3)
 75%|███████▌  | 947/1261 [05:19<01:45,  2.97it/s]
746.210613267 m 266.669351592 m 506.43998243 m
Image shape: (720, 1280, 3)
 75%|███████▌  | 948/1261 [05:19<01:44,  2.99it/s]
742.880190787 m 301.226981741 m 522.053586264 m
Image shape: (720, 1280, 3)
 75%|███████▌  | 949/1261 [05:19<01:43,  3.00it/s]
842.362248226 m 327.470500818 m 584.916374522 m
Image shape: (720, 1280, 3)
 75%|███████▌  | 950/1261 [05:20<01:43,  3.01it/s]
785.317040161 m 559.794323087 m 672.555681624 m
Image shape: (720, 1280, 3)
 75%|███████▌  | 951/1261 [05:20<01:43,  3.00it/s]
812.188150055 m 387.371385092 m 599.779767573 m
Image shape: (720, 1280, 3)
 75%|███████▌  | 952/1261 [05:20<01:42,  3.00it/s]
987.806075457 m 350.893152183 m 669.34961382 m
Image shape: (720, 1280, 3)
 76%|███████▌  | 953/1261 [05:21<01:42,  3.01it/s]
1010.12096773 m 287.880367559 m 649.000667647 m
Image shape: (720, 1280, 3)
 76%|███████▌  | 954/1261 [05:21<01:41,  3.01it/s]
1120.97564909 m 290.5887458 m 705.782197447 m
Image shape: (720, 1280, 3)
 76%|███████▌  | 955/1261 [05:21<01:41,  3.00it/s]
827.478422826 m 325.725014098 m 576.601718462 m
Image shape: (720, 1280, 3)
 76%|███████▌  | 956/1261 [05:22<01:41,  3.01it/s]
577.821889731 m 326.709830545 m 452.265860138 m
Image shape: (720, 1280, 3)
 76%|███████▌  | 957/1261 [05:22<01:40,  3.02it/s]
704.999280904 m 306.353299902 m 505.676290403 m
Image shape: (720, 1280, 3)
 76%|███████▌  | 958/1261 [05:22<01:40,  3.02it/s]
699.180384871 m 322.996620918 m 511.088502895 m
Image shape: (720, 1280, 3)
 76%|███████▌  | 959/1261 [05:23<01:40,  3.01it/s]
579.332116182 m 333.357507591 m 456.344811887 m
Image shape: (720, 1280, 3)
 76%|███████▌  | 960/1261 [05:23<01:40,  2.99it/s]
589.312946365 m 628.331622079 m 608.822284222 m
Image shape: (720, 1280, 3)
 76%|███████▌  | 961/1261 [05:23<01:40,  2.98it/s]
688.232122834 m 1082.25982192 m 885.245972375 m
Image shape: (720, 1280, 3)
 76%|███████▋  | 962/1261 [05:24<01:40,  2.99it/s]
642.124456707 m 1310.411011 m 976.267733856 m
Image shape: (720, 1280, 3)
 76%|███████▋  | 963/1261 [05:24<01:39,  3.00it/s]
606.865691295 m 452.30560302 m 529.585647158 m
Image shape: (720, 1280, 3)
 76%|███████▋  | 964/1261 [05:24<01:38,  3.01it/s]
677.782172173 m 381.451958726 m 529.61706545 m
Image shape: (720, 1280, 3)
 77%|███████▋  | 965/1261 [05:25<01:37,  3.02it/s]
590.744245007 m 324.47333601 m 457.608790508 m
Image shape: (720, 1280, 3)
 77%|███████▋  | 966/1261 [05:25<01:37,  3.03it/s]
610.591929628 m 307.545946767 m 459.068938198 m
Image shape: (720, 1280, 3)
 77%|███████▋  | 967/1261 [05:25<01:36,  3.05it/s]
584.099334311 m 288.714567986 m 436.406951149 m
Image shape: (720, 1280, 3)
 77%|███████▋  | 968/1261 [05:26<01:36,  3.03it/s]
687.055063375 m 298.782057536 m 492.918560455 m
Image shape: (720, 1280, 3)
 77%|███████▋  | 969/1261 [05:26<01:35,  3.04it/s]
833.268025089 m 284.462853549 m 558.865439319 m
Image shape: (720, 1280, 3)
 77%|███████▋  | 970/1261 [05:26<01:35,  3.04it/s]
827.351745608 m 289.259125402 m 558.305435505 m
Image shape: (720, 1280, 3)
 77%|███████▋  | 971/1261 [05:27<01:35,  3.05it/s]
634.139198547 m 466.997391639 m 550.568295093 m
Image shape: (720, 1280, 3)
 77%|███████▋  | 972/1261 [05:27<01:35,  3.04it/s]
637.327169421 m 321.488150356 m 479.407659888 m
Image shape: (720, 1280, 3)
 77%|███████▋  | 973/1261 [05:27<01:35,  3.02it/s]
988.088247808 m 440.036220133 m 714.062233971 m
Image shape: (720, 1280, 3)
 77%|███████▋  | 974/1261 [05:28<01:34,  3.03it/s]
2432.97933008 m 593.369860732 m 1513.17459541 m
Image shape: (720, 1280, 3)
 77%|███████▋  | 975/1261 [05:28<01:34,  3.01it/s]
5357.48838581 m 469.67069663 m 2913.57954122 m
Image shape: (720, 1280, 3)
 77%|███████▋  | 976/1261 [05:28<01:34,  3.02it/s]
10795.7192026 m 427.581870679 m 5611.65053663 m
Image shape: (720, 1280, 3)
 77%|███████▋  | 977/1261 [05:29<01:34,  3.01it/s]
2514.30252601 m 452.577863635 m 1483.44019482 m
Image shape: (720, 1280, 3)
 78%|███████▊  | 978/1261 [05:29<01:34,  2.98it/s]
1091.08652394 m 515.744028975 m 803.415276459 m
Image shape: (720, 1280, 3)
 78%|███████▊  | 979/1261 [05:29<01:35,  2.97it/s]
809.914314035 m 508.324667161 m 659.119490598 m
Image shape: (720, 1280, 3)
 78%|███████▊  | 980/1261 [05:30<01:35,  2.95it/s]
1054.73187425 m 17145.804978 m 9100.26842614 m
Image shape: (720, 1280, 3)
 78%|███████▊  | 981/1261 [05:30<01:35,  2.93it/s]
1115.01230872 m 2645.4933247 m 1880.25281671 m
Image shape: (720, 1280, 3)
 78%|███████▊  | 982/1261 [05:30<01:35,  2.91it/s]
1116.29245757 m 2144.36788493 m 1630.33017125 m
Image shape: (720, 1280, 3)
 78%|███████▊  | 983/1261 [05:31<01:35,  2.91it/s]
1082.14427417 m 1877.74900542 m 1479.9466398 m
Image shape: (720, 1280, 3)
 78%|███████▊  | 984/1261 [05:31<01:47,  2.58it/s]
1217.90282729 m 1372.75322046 m 1295.32802388 m
Image shape: (720, 1280, 3)
 78%|███████▊  | 985/1261 [05:32<01:48,  2.56it/s]
1902.25658286 m 1027.9304109 m 1465.09349688 m
Image shape: (720, 1280, 3)
 78%|███████▊  | 986/1261 [05:32<01:46,  2.59it/s]
1835.59654414 m 441.006942607 m 1138.30174337 m
Image shape: (720, 1280, 3)
 78%|███████▊  | 987/1261 [05:32<01:45,  2.60it/s]
7427.49771152 m 340.088803053 m 3883.79325728 m
Image shape: (720, 1280, 3)
 78%|███████▊  | 988/1261 [05:33<01:45,  2.58it/s]
6786.17996572 m 280.827370546 m 3533.50366813 m
Image shape: (720, 1280, 3)
 78%|███████▊  | 989/1261 [05:33<01:45,  2.58it/s]
7411.0431896 m 260.629596104 m 3835.83639285 m
Image shape: (720, 1280, 3)
 79%|███████▊  | 990/1261 [05:33<01:45,  2.58it/s]
8565.93123123 m 235.186354594 m 4400.55879291 m
Image shape: (720, 1280, 3)
 79%|███████▊  | 991/1261 [05:34<01:45,  2.57it/s]
3532.8092956 m 2222.74340315 m 2877.77634938 m
Image shape: (720, 1280, 3)
 79%|███████▊  | 992/1261 [05:34<01:46,  2.53it/s]
2570.89832932 m 2889.17609791 m 2730.03721361 m
Image shape: (720, 1280, 3)
 79%|███████▊  | 993/1261 [05:35<01:46,  2.51it/s]
2527.90773515 m 803.462950785 m 1665.68534297 m
Image shape: (720, 1280, 3)
 79%|███████▉  | 994/1261 [05:35<01:47,  2.48it/s]
6533.08986768 m 658.762087552 m 3595.92597761 m
Image shape: (720, 1280, 3)
 79%|███████▉  | 995/1261 [05:36<01:47,  2.47it/s]
6522.23476128 m 1852.16596088 m 4187.20036108 m
Image shape: (720, 1280, 3)
 79%|███████▉  | 996/1261 [05:36<01:48,  2.45it/s]
10930.6432833 m 3299.34657598 m 7114.99492962 m
Image shape: (720, 1280, 3)
 79%|███████▉  | 997/1261 [05:36<01:48,  2.44it/s]
10351.3417749 m 126005.429105 m 68178.3854402 m
Image shape: (720, 1280, 3)
 79%|███████▉  | 998/1261 [05:37<01:48,  2.42it/s]
11237.9824695 m 1473.65996748 m 6355.82121851 m
Image shape: (720, 1280, 3)
 79%|███████▉  | 999/1261 [05:37<01:49,  2.40it/s]
7541.06596469 m 908.034571661 m 4224.55026818 m
Image shape: (720, 1280, 3)
 79%|███████▉  | 1000/1261 [05:38<01:48,  2.41it/s]
6371.85427646 m 4035.30308766 m 5203.57868206 m
Image shape: (720, 1280, 3)
 79%|███████▉  | 1001/1261 [05:38<01:47,  2.42it/s]
4382.12790952 m 3417.57463662 m 3899.85127307 m
Image shape: (720, 1280, 3)
 79%|███████▉  | 1002/1261 [05:38<01:46,  2.43it/s]
4744.70721603 m 1607.46135579 m 3176.08428591 m
Image shape: (720, 1280, 3)
 80%|███████▉  | 1003/1261 [05:39<01:45,  2.44it/s]
4100.94179836 m 909.245364302 m 2505.09358133 m
Image shape: (720, 1280, 3)
 80%|███████▉  | 1004/1261 [05:39<01:44,  2.45it/s]
3888.6710864 m 1515.31447602 m 2701.99278121 m
Image shape: (720, 1280, 3)
 80%|███████▉  | 1005/1261 [05:40<01:43,  2.47it/s]
2889.11557859 m 1421.03366328 m 2155.07462094 m
Image shape: (720, 1280, 3)
 80%|███████▉  | 1006/1261 [05:40<01:43,  2.46it/s]
11125.6425897 m 1890.1248523 m 6507.88372101 m
Image shape: (720, 1280, 3)
 80%|███████▉  | 1007/1261 [05:40<01:43,  2.46it/s]
2986.18562023 m 622.459931958 m 1804.32277609 m
Image shape: (720, 1280, 3)
 80%|███████▉  | 1008/1261 [05:41<01:41,  2.50it/s]
2433.28356228 m 304.28585831 m 1368.78471029 m
Image shape: (720, 1280, 3)
 80%|████████  | 1009/1261 [05:41<01:39,  2.53it/s]
1435.99474331 m 332.334061653 m 884.164402484 m
Image shape: (720, 1280, 3)
 80%|████████  | 1010/1261 [05:42<01:39,  2.53it/s]
1813.04903308 m 351.605262677 m 1082.32714788 m
Image shape: (720, 1280, 3)
 80%|████████  | 1011/1261 [05:42<01:37,  2.57it/s]
2296.34880584 m 331.733298901 m 1314.04105237 m
Image shape: (720, 1280, 3)
 80%|████████  | 1012/1261 [05:42<01:35,  2.60it/s]
1614.3680495 m 423.420573995 m 1018.89431175 m
Image shape: (720, 1280, 3)
 80%|████████  | 1013/1261 [05:43<01:34,  2.62it/s]
1723.4238366 m 345.077893473 m 1034.25086504 m
Image shape: (720, 1280, 3)
 80%|████████  | 1014/1261 [05:43<01:33,  2.66it/s]
1214.02899434 m 441.987322511 m 828.008158427 m
Image shape: (720, 1280, 3)
 80%|████████  | 1015/1261 [05:43<01:32,  2.67it/s]
1036.06775889 m 381.44323022 m 708.755494555 m
Image shape: (720, 1280, 3)
 81%|████████  | 1016/1261 [05:44<01:31,  2.68it/s]
714.99122235 m 254.705466665 m 484.848344508 m
Image shape: (720, 1280, 3)
 81%|████████  | 1017/1261 [05:44<01:30,  2.71it/s]
759.859418381 m 239.929174504 m 499.894296442 m
Image shape: (720, 1280, 3)
 81%|████████  | 1018/1261 [05:45<01:29,  2.71it/s]
438.226564806 m 425.100038051 m 431.663301429 m
Image shape: (720, 1280, 3)
 81%|████████  | 1019/1261 [05:45<01:28,  2.72it/s]
338.973824295 m 392.381412503 m 365.677618399 m
Image shape: (720, 1280, 3)
 81%|████████  | 1020/1261 [05:45<01:28,  2.73it/s]
296.317134141 m 542.059682419 m 419.18840828 m
Image shape: (720, 1280, 3)
 81%|████████  | 1021/1261 [05:46<01:27,  2.76it/s]
249.572668084 m 195.730814221 m 222.651741153 m
Image shape: (720, 1280, 3)
 81%|████████  | 1022/1261 [05:46<01:26,  2.77it/s]
256.547248082 m 297.732456392 m 277.139852237 m
Image shape: (720, 1280, 3)
 81%|████████  | 1023/1261 [05:46<01:25,  2.78it/s]
265.693068273 m 366.482103417 m 316.087585845 m
Image shape: (720, 1280, 3)
 81%|████████  | 1024/1261 [05:47<01:24,  2.80it/s]
258.547532437 m 412.207058686 m 335.377295562 m
Image shape: (720, 1280, 3)
 81%|████████▏ | 1025/1261 [05:47<01:23,  2.82it/s]
306.63013603 m 167.305402258 m 236.967769144 m
Image shape: (720, 1280, 3)
 81%|████████▏ | 1026/1261 [05:47<01:22,  2.84it/s]
306.802388352 m 297.211035759 m 302.006712056 m
Image shape: (720, 1280, 3)
 81%|████████▏ | 1027/1261 [05:48<01:21,  2.86it/s]
241.14544093 m 200.881361742 m 221.013401336 m
Image shape: (720, 1280, 3)
 82%|████████▏ | 1028/1261 [05:48<01:20,  2.90it/s]
170.983220999 m 226.667276104 m 198.825248551 m
Image shape: (720, 1280, 3)
 82%|████████▏ | 1029/1261 [05:48<01:19,  2.93it/s]
202.186389503 m 190.829169671 m 196.507779587 m
Image shape: (720, 1280, 3)
 82%|████████▏ | 1030/1261 [05:49<01:17,  2.96it/s]
246.96980138 m 243.572308217 m 245.271054798 m
Image shape: (720, 1280, 3)
 82%|████████▏ | 1031/1261 [05:49<01:17,  2.98it/s]
207.247106447 m 248.614767427 m 227.930936937 m
Image shape: (720, 1280, 3)
 82%|████████▏ | 1032/1261 [05:49<01:16,  3.00it/s]
261.661972302 m 278.173276902 m 269.917624602 m
Image shape: (720, 1280, 3)
 82%|████████▏ | 1033/1261 [05:50<01:16,  3.00it/s]
424.006300569 m 393.998297806 m 409.002299188 m
Image shape: (720, 1280, 3)
 82%|████████▏ | 1034/1261 [05:50<01:14,  3.03it/s]
621.729347666 m 809.724216326 m 715.726781996 m
Image shape: (720, 1280, 3)
 82%|████████▏ | 1035/1261 [05:50<01:14,  3.04it/s]
692.437542315 m 430.569449553 m 561.503495934 m
Image shape: (720, 1280, 3)
 82%|████████▏ | 1036/1261 [05:51<01:13,  3.05it/s]
700.802303199 m 266.136438999 m 483.469371099 m
Image shape: (720, 1280, 3)
 82%|████████▏ | 1037/1261 [05:51<01:13,  3.06it/s]
821.985531608 m 276.535994181 m 549.260762894 m
Image shape: (720, 1280, 3)
 82%|████████▏ | 1038/1261 [05:51<01:12,  3.06it/s]
573.012956533 m 260.878576681 m 416.945766607 m
Image shape: (720, 1280, 3)
 82%|████████▏ | 1039/1261 [05:52<01:12,  3.05it/s]
479.886972699 m 293.682662835 m 386.784817767 m
Image shape: (720, 1280, 3)
 82%|████████▏ | 1040/1261 [05:52<01:12,  3.06it/s]
524.784702783 m 324.081170584 m 424.432936684 m
Image shape: (720, 1280, 3)
 83%|████████▎ | 1041/1261 [05:52<01:12,  3.05it/s]
567.120117654 m 194.368200135 m 380.744158895 m
Image shape: (720, 1280, 3)
 83%|████████▎ | 1042/1261 [05:53<01:11,  3.06it/s]
589.361115954 m 1060.26499289 m 824.813054423 m
Image shape: (720, 1280, 3)
 83%|████████▎ | 1043/1261 [05:53<01:11,  3.07it/s]
546.146962063 m 578.480662924 m 562.313812494 m
Image shape: (720, 1280, 3)
 83%|████████▎ | 1044/1261 [05:53<01:10,  3.07it/s]
398.715482499 m 689.168664123 m 543.942073311 m
Image shape: (720, 1280, 3)
 83%|████████▎ | 1045/1261 [05:54<01:10,  3.07it/s]
427.509870706 m 582.705108383 m 505.107489545 m
Image shape: (720, 1280, 3)
 83%|████████▎ | 1046/1261 [05:54<01:10,  3.07it/s]
312.033804309 m 547.476320448 m 429.755062379 m
Image shape: (720, 1280, 3)
 83%|████████▎ | 1047/1261 [05:54<01:09,  3.07it/s]
350.425004142 m 302.602472756 m 326.513738449 m
Image shape: (720, 1280, 3)
 83%|████████▎ | 1048/1261 [05:55<01:09,  3.07it/s]
478.734531415 m 295.042644883 m 386.888588149 m
Image shape: (720, 1280, 3)
 83%|████████▎ | 1049/1261 [05:55<01:09,  3.05it/s]
477.524826663 m 235.585791927 m 356.555309295 m
Image shape: (720, 1280, 3)
 83%|████████▎ | 1050/1261 [05:55<01:09,  3.04it/s]
532.817047976 m 272.35667538 m 402.586861678 m
Image shape: (720, 1280, 3)
 83%|████████▎ | 1051/1261 [05:56<01:09,  3.04it/s]
598.92107811 m 245.801646096 m 422.361362103 m
Image shape: (720, 1280, 3)
 83%|████████▎ | 1052/1261 [05:56<01:08,  3.03it/s]
682.575932998 m 282.309719231 m 482.442826115 m
Image shape: (720, 1280, 3)
 84%|████████▎ | 1053/1261 [05:56<01:08,  3.03it/s]
1263.34996149 m 237.047223864 m 750.198592678 m
Image shape: (720, 1280, 3)
 84%|████████▎ | 1054/1261 [05:57<01:08,  3.01it/s]
1022.02399807 m 174.512225925 m 598.268111998 m
Image shape: (720, 1280, 3)
 84%|████████▎ | 1055/1261 [05:57<01:10,  2.93it/s]
1157.2250246 m 262.590886676 m 709.907955638 m
Image shape: (720, 1280, 3)
 84%|████████▎ | 1056/1261 [05:57<01:10,  2.89it/s]
1374.02938563 m 703.020297005 m 1038.52484132 m
Image shape: (720, 1280, 3)
 84%|████████▍ | 1057/1261 [05:58<01:10,  2.87it/s]
757.934439661 m 954.442958332 m 856.188698997 m
Image shape: (720, 1280, 3)
 84%|████████▍ | 1058/1261 [05:58<01:09,  2.92it/s]
739.220716949 m 522.790204277 m 631.005460613 m
Image shape: (720, 1280, 3)
 84%|████████▍ | 1059/1261 [05:58<01:08,  2.94it/s]
700.22485799 m 389.675844587 m 544.950351288 m
Image shape: (720, 1280, 3)
 84%|████████▍ | 1060/1261 [05:59<01:07,  2.97it/s]
716.030737929 m 303.320905485 m 509.675821707 m
Image shape: (720, 1280, 3)
 84%|████████▍ | 1061/1261 [05:59<01:07,  2.96it/s]
549.992476098 m 463.044941051 m 506.518708574 m
Image shape: (720, 1280, 3)
 84%|████████▍ | 1062/1261 [05:59<01:06,  2.97it/s]
620.369275424 m 348.879822479 m 484.624548951 m
Image shape: (720, 1280, 3)
 84%|████████▍ | 1063/1261 [06:00<01:06,  2.97it/s]
749.715333254 m 326.661102301 m 538.188217777 m
Image shape: (720, 1280, 3)
 84%|████████▍ | 1064/1261 [06:00<01:05,  2.99it/s]
905.843608827 m 368.940737115 m 637.392172971 m
Image shape: (720, 1280, 3)
 84%|████████▍ | 1065/1261 [06:00<01:05,  2.99it/s]
972.423579268 m 366.603480756 m 669.513530012 m
Image shape: (720, 1280, 3)
 85%|████████▍ | 1066/1261 [06:01<01:05,  2.99it/s]
1257.94266837 m 381.621310011 m 819.781989191 m
Image shape: (720, 1280, 3)
 85%|████████▍ | 1067/1261 [06:01<01:04,  3.00it/s]
1186.27579241 m 460.433608233 m 823.354700323 m
Image shape: (720, 1280, 3)
 85%|████████▍ | 1068/1261 [06:01<01:04,  2.99it/s]
1309.08185723 m 569.089868435 m 939.085862832 m
Image shape: (720, 1280, 3)
 85%|████████▍ | 1069/1261 [06:02<01:04,  2.98it/s]
1374.9643988 m 564.80544814 m 969.884923471 m
Image shape: (720, 1280, 3)
 85%|████████▍ | 1070/1261 [06:02<01:04,  2.98it/s]
1016.91147369 m 410.293746314 m 713.60261 m
Image shape: (720, 1280, 3)
 85%|████████▍ | 1071/1261 [06:02<01:03,  2.99it/s]
956.336190877 m 349.054225933 m 652.695208405 m
Image shape: (720, 1280, 3)
 85%|████████▌ | 1072/1261 [06:03<01:03,  2.98it/s]
730.572258391 m 272.799346244 m 501.685802318 m
Image shape: (720, 1280, 3)
 85%|████████▌ | 1073/1261 [06:03<01:03,  2.97it/s]
917.906108734 m 326.209515379 m 622.057812056 m
Image shape: (720, 1280, 3)
 85%|████████▌ | 1074/1261 [06:03<01:03,  2.96it/s]
910.532776819 m 312.688874434 m 611.610825626 m
Image shape: (720, 1280, 3)
 85%|████████▌ | 1075/1261 [06:04<01:02,  2.96it/s]
946.881499463 m 420.545462733 m 683.713481098 m
Image shape: (720, 1280, 3)
 85%|████████▌ | 1076/1261 [06:04<01:02,  2.96it/s]
813.049001539 m 312.30835829 m 562.678679915 m
Image shape: (720, 1280, 3)
 85%|████████▌ | 1077/1261 [06:04<01:02,  2.96it/s]
831.111955477 m 333.428969592 m 582.270462535 m
Image shape: (720, 1280, 3)
 85%|████████▌ | 1078/1261 [06:05<01:01,  2.98it/s]
843.944713157 m 378.280549033 m 611.112631095 m
Image shape: (720, 1280, 3)
 86%|████████▌ | 1079/1261 [06:05<01:00,  2.99it/s]
799.252511982 m 461.202140807 m 630.227326395 m
Image shape: (720, 1280, 3)
 86%|████████▌ | 1080/1261 [06:05<01:00,  3.00it/s]
818.169405646 m 478.913011338 m 648.541208492 m
Image shape: (720, 1280, 3)
 86%|████████▌ | 1081/1261 [06:06<00:59,  3.00it/s]
1077.05388449 m 590.426104386 m 833.739994436 m
Image shape: (720, 1280, 3)
 86%|████████▌ | 1082/1261 [06:06<00:59,  3.00it/s]
1105.37158444 m 401.550267086 m 753.460925765 m
Image shape: (720, 1280, 3)
 86%|████████▌ | 1083/1261 [06:06<00:59,  3.01it/s]
894.043918044 m 346.640210838 m 620.342064441 m
Image shape: (720, 1280, 3)
 86%|████████▌ | 1084/1261 [06:07<00:58,  3.01it/s]
812.347894452 m 291.362523285 m 551.855208868 m
Image shape: (720, 1280, 3)
 86%|████████▌ | 1085/1261 [06:07<00:58,  3.02it/s]
997.157007099 m 334.464903466 m 665.810955282 m
Image shape: (720, 1280, 3)
 86%|████████▌ | 1086/1261 [06:07<00:57,  3.02it/s]
1178.94263628 m 334.298156667 m 756.620396473 m
Image shape: (720, 1280, 3)
 86%|████████▌ | 1087/1261 [06:08<00:57,  3.02it/s]
1079.49943603 m 376.57932003 m 728.03937803 m
Image shape: (720, 1280, 3)
 86%|████████▋ | 1088/1261 [06:08<00:57,  3.00it/s]
928.117062437 m 350.129060182 m 639.12306131 m
Image shape: (720, 1280, 3)
 86%|████████▋ | 1089/1261 [06:08<00:56,  3.02it/s]
889.698204314 m 375.616385689 m 632.657295001 m
Image shape: (720, 1280, 3)
 86%|████████▋ | 1090/1261 [06:09<00:56,  3.02it/s]
905.598554759 m 368.079519553 m 636.839037156 m
Image shape: (720, 1280, 3)
 87%|████████▋ | 1091/1261 [06:09<00:56,  3.02it/s]
1020.76831822 m 433.468004785 m 727.1181615 m
Image shape: (720, 1280, 3)
 87%|████████▋ | 1092/1261 [06:09<00:56,  3.00it/s]
944.459976965 m 455.902520794 m 700.181248879 m
Image shape: (720, 1280, 3)
 87%|████████▋ | 1093/1261 [06:10<00:55,  3.00it/s]
1045.55831945 m 417.834190582 m 731.696255017 m
Image shape: (720, 1280, 3)
 87%|████████▋ | 1094/1261 [06:10<00:55,  3.01it/s]
1232.1791665 m 325.210940489 m 778.695053497 m
Image shape: (720, 1280, 3)
 87%|████████▋ | 1095/1261 [06:10<00:54,  3.02it/s]
1148.69182835 m 288.443741073 m 718.567784711 m
Image shape: (720, 1280, 3)
 87%|████████▋ | 1096/1261 [06:11<00:54,  3.01it/s]
1527.39796924 m 324.841380912 m 926.119675078 m
Image shape: (720, 1280, 3)
 87%|████████▋ | 1097/1261 [06:11<00:54,  3.00it/s]
1375.71132125 m 335.475073611 m 855.593197429 m
Image shape: (720, 1280, 3)
 87%|████████▋ | 1098/1261 [06:11<00:54,  3.00it/s]
1615.3125963 m 409.648604635 m 1012.48060047 m
Image shape: (720, 1280, 3)
 87%|████████▋ | 1099/1261 [06:12<00:53,  3.02it/s]
1921.23297596 m 334.706322127 m 1127.96964904 m
Image shape: (720, 1280, 3)
 87%|████████▋ | 1100/1261 [06:12<00:53,  3.01it/s]
2181.58390845 m 356.782621269 m 1269.18326486 m
Image shape: (720, 1280, 3)
 87%|████████▋ | 1101/1261 [06:12<00:52,  3.02it/s]
1452.31724731 m 421.137195116 m 936.727221213 m
Image shape: (720, 1280, 3)
 87%|████████▋ | 1102/1261 [06:13<00:52,  3.03it/s]
1840.4912224 m 508.56253623 m 1174.52687931 m
Image shape: (720, 1280, 3)
 87%|████████▋ | 1103/1261 [06:13<00:52,  3.02it/s]
1389.23097519 m 670.617040292 m 1029.92400774 m
Image shape: (720, 1280, 3)
 88%|████████▊ | 1104/1261 [06:13<00:51,  3.03it/s]
2027.89232015 m 828.907738742 m 1428.40002945 m
Image shape: (720, 1280, 3)
 88%|████████▊ | 1105/1261 [06:14<00:51,  3.04it/s]
1752.20772988 m 425.567580019 m 1088.88765495 m
Image shape: (720, 1280, 3)
 88%|████████▊ | 1106/1261 [06:14<00:50,  3.04it/s]
975.896477315 m 433.682168823 m 704.789323069 m
Image shape: (720, 1280, 3)
 88%|████████▊ | 1107/1261 [06:14<00:50,  3.03it/s]
1028.64517294 m 325.685018212 m 677.165095578 m
Image shape: (720, 1280, 3)
 88%|████████▊ | 1108/1261 [06:15<00:50,  3.02it/s]
903.195918178 m 471.385860448 m 687.290889313 m
Image shape: (720, 1280, 3)
 88%|████████▊ | 1109/1261 [06:15<00:50,  3.01it/s]
898.169363471 m 461.74862903 m 679.958996251 m
Image shape: (720, 1280, 3)
 88%|████████▊ | 1110/1261 [06:15<00:50,  2.97it/s]
774.615824356 m 517.642360104 m 646.12909223 m
Image shape: (720, 1280, 3)
 88%|████████▊ | 1111/1261 [06:16<00:50,  2.97it/s]
892.591482933 m 342.625559105 m 617.608521019 m
Image shape: (720, 1280, 3)
 88%|████████▊ | 1112/1261 [06:16<00:50,  2.97it/s]
980.678412043 m 336.147899926 m 658.413155984 m
Image shape: (720, 1280, 3)
 88%|████████▊ | 1113/1261 [06:16<00:49,  2.97it/s]
1215.81213114 m 362.976490328 m 789.394310733 m
Image shape: (720, 1280, 3)
 88%|████████▊ | 1114/1261 [06:17<00:49,  2.99it/s]
1342.65322088 m 384.091784757 m 863.37250282 m
Image shape: (720, 1280, 3)
 88%|████████▊ | 1115/1261 [06:17<00:48,  3.01it/s]
1665.50911517 m 375.842501768 m 1020.67580847 m
Image shape: (720, 1280, 3)
 89%|████████▊ | 1116/1261 [06:17<00:48,  3.02it/s]
1277.09097012 m 390.840530553 m 833.965750338 m
Image shape: (720, 1280, 3)
 89%|████████▊ | 1117/1261 [06:18<00:47,  3.03it/s]
1084.86767404 m 375.782527714 m 730.325100878 m
Image shape: (720, 1280, 3)
 89%|████████▊ | 1118/1261 [06:18<00:47,  3.02it/s]
1386.94766779 m 337.531078347 m 862.239373068 m
Image shape: (720, 1280, 3)
 89%|████████▊ | 1119/1261 [06:18<00:48,  2.95it/s]
1911.18042899 m 388.128009802 m 1149.6542194 m
Image shape: (720, 1280, 3)
 89%|████████▉ | 1120/1261 [06:19<00:47,  2.96it/s]
2795.37940019 m 319.372821609 m 1557.3761109 m
Image shape: (720, 1280, 3)
 89%|████████▉ | 1121/1261 [06:19<00:47,  2.98it/s]
3991.86899276 m 334.335743295 m 2163.10236803 m
Image shape: (720, 1280, 3)
 89%|████████▉ | 1122/1261 [06:19<00:46,  3.00it/s]
4825.79904626 m 316.928616108 m 2571.36383118 m
Image shape: (720, 1280, 3)
 89%|████████▉ | 1123/1261 [06:20<00:45,  3.01it/s]
10885.302877 m 340.001110801 m 5612.65199392 m
Image shape: (720, 1280, 3)
 89%|████████▉ | 1124/1261 [06:20<00:45,  3.02it/s]
3985.90367577 m 386.213549218 m 2186.05861249 m
Image shape: (720, 1280, 3)
 89%|████████▉ | 1125/1261 [06:20<00:44,  3.03it/s]
2069.98568736 m 467.794522437 m 1268.8901049 m
Image shape: (720, 1280, 3)
 89%|████████▉ | 1126/1261 [06:21<00:44,  3.02it/s]
1301.50369912 m 564.512801931 m 933.008250525 m
Image shape: (720, 1280, 3)
 89%|████████▉ | 1127/1261 [06:21<00:44,  3.03it/s]
1109.9340278 m 889.522500962 m 999.72826438 m
Image shape: (720, 1280, 3)
 89%|████████▉ | 1128/1261 [06:21<00:43,  3.03it/s]
966.817469065 m 293.945305279 m 630.381387172 m
Image shape: (720, 1280, 3)
 90%|████████▉ | 1129/1261 [06:22<00:43,  3.05it/s]
766.772445466 m 351.206592979 m 558.989519223 m
Image shape: (720, 1280, 3)
 90%|████████▉ | 1130/1261 [06:22<00:42,  3.05it/s]
664.111913439 m 330.22432342 m 497.16811843 m
Image shape: (720, 1280, 3)
 90%|████████▉ | 1131/1261 [06:22<00:42,  3.05it/s]
594.510754245 m 362.343655402 m 478.427204823 m
Image shape: (720, 1280, 3)
 90%|████████▉ | 1132/1261 [06:23<00:43,  2.99it/s]
614.847442766 m 365.924968279 m 490.386205522 m
Image shape: (720, 1280, 3)
 90%|████████▉ | 1133/1261 [06:23<00:44,  2.91it/s]
703.395142217 m 372.389209371 m 537.892175794 m
Image shape: (720, 1280, 3)
 90%|████████▉ | 1134/1261 [06:23<00:43,  2.89it/s]
898.696378634 m 330.302715772 m 614.499547203 m
Image shape: (720, 1280, 3)
 90%|█████████ | 1135/1261 [06:24<00:42,  2.94it/s]
909.137165245 m 381.837293579 m 645.487229412 m
Image shape: (720, 1280, 3)
 90%|█████████ | 1136/1261 [06:24<00:42,  2.96it/s]
1031.1051785 m 439.850839175 m 735.478008838 m
Image shape: (720, 1280, 3)
 90%|█████████ | 1137/1261 [06:24<00:41,  2.98it/s]
1061.16695113 m 486.980594356 m 774.073772743 m
Image shape: (720, 1280, 3)
 90%|█████████ | 1138/1261 [06:25<00:41,  3.00it/s]
1206.7241795 m 702.839694978 m 954.781937241 m
Image shape: (720, 1280, 3)
 90%|█████████ | 1139/1261 [06:25<00:40,  3.01it/s]
1302.85294792 m 496.918907651 m 899.885927783 m
Image shape: (720, 1280, 3)
 90%|█████████ | 1140/1261 [06:25<00:40,  3.02it/s]
932.313910303 m 357.475856228 m 644.894883266 m
Image shape: (720, 1280, 3)
 90%|█████████ | 1141/1261 [06:26<00:39,  3.03it/s]
1613.40933288 m 309.942985874 m 961.676159375 m
Image shape: (720, 1280, 3)
 91%|█████████ | 1142/1261 [06:26<00:39,  3.01it/s]
1761.05578559 m 468.00051723 m 1114.52815141 m
Image shape: (720, 1280, 3)
 91%|█████████ | 1143/1261 [06:26<00:39,  3.02it/s]
2562.83709625 m 376.056168562 m 1469.44663241 m
Image shape: (720, 1280, 3)
 91%|█████████ | 1144/1261 [06:27<00:38,  3.04it/s]
3032.09086696 m 637.791275032 m 1834.941071 m
Image shape: (720, 1280, 3)
 91%|█████████ | 1145/1261 [06:27<00:38,  3.05it/s]
1415.68915647 m 336.940542069 m 876.314849267 m
Image shape: (720, 1280, 3)
 91%|█████████ | 1146/1261 [06:27<00:37,  3.04it/s]
1615.33099189 m 329.470155659 m 972.400573777 m
Image shape: (720, 1280, 3)
 91%|█████████ | 1147/1261 [06:28<00:37,  3.02it/s]
1843.79447803 m 351.577225049 m 1097.68585154 m
Image shape: (720, 1280, 3)
 91%|█████████ | 1148/1261 [06:28<00:37,  3.03it/s]
1254.06634806 m 471.927665079 m 862.997006568 m
Image shape: (720, 1280, 3)
 91%|█████████ | 1149/1261 [06:28<00:37,  3.01it/s]
1242.32724407 m 375.014056649 m 808.670650361 m
Image shape: (720, 1280, 3)
 91%|█████████ | 1150/1261 [06:29<00:36,  3.01it/s]
1003.66278687 m 446.590218181 m 725.126502525 m
Image shape: (720, 1280, 3)
 91%|█████████▏| 1151/1261 [06:29<00:36,  3.02it/s]
743.687864375 m 414.358211256 m 579.023037816 m
Image shape: (720, 1280, 3)
 91%|█████████▏| 1152/1261 [06:29<00:36,  3.02it/s]
850.963870554 m 297.33918202 m 574.151526287 m
Image shape: (720, 1280, 3)
 91%|█████████▏| 1153/1261 [06:30<00:35,  3.03it/s]
782.134455278 m 351.976238959 m 567.055347119 m
Image shape: (720, 1280, 3)
 92%|█████████▏| 1154/1261 [06:30<00:35,  3.03it/s]
752.756081456 m 347.400951136 m 550.078516296 m
Image shape: (720, 1280, 3)
 92%|█████████▏| 1155/1261 [06:30<00:34,  3.04it/s]
875.560228926 m 405.454556422 m 640.507392674 m
Image shape: (720, 1280, 3)
 92%|█████████▏| 1156/1261 [06:31<00:34,  3.03it/s]
1202.81503946 m 323.544228494 m 763.179633977 m
Image shape: (720, 1280, 3)
 92%|█████████▏| 1157/1261 [06:31<00:34,  3.01it/s]
1034.82748241 m 310.499249336 m 672.663365871 m
Image shape: (720, 1280, 3)
 92%|█████████▏| 1158/1261 [06:31<00:34,  3.00it/s]
972.70494009 m 332.012045536 m 652.358492813 m
Image shape: (720, 1280, 3)
 92%|█████████▏| 1159/1261 [06:32<00:33,  3.00it/s]
974.449462854 m 558.703932309 m 766.576697582 m
Image shape: (720, 1280, 3)
 92%|█████████▏| 1160/1261 [06:32<00:33,  3.00it/s]
1013.64428029 m 453.658929631 m 733.651604961 m
Image shape: (720, 1280, 3)
 92%|█████████▏| 1161/1261 [06:32<00:33,  3.01it/s]
906.745848008 m 524.552234544 m 715.649041276 m
Image shape: (720, 1280, 3)
 92%|█████████▏| 1162/1261 [06:33<00:33,  2.99it/s]
925.865948513 m 385.066903096 m 655.466425804 m
Image shape: (720, 1280, 3)
 92%|█████████▏| 1163/1261 [06:33<00:32,  2.99it/s]
818.400518648 m 327.244191856 m 572.822355252 m
Image shape: (720, 1280, 3)
 92%|█████████▏| 1164/1261 [06:33<00:32,  3.00it/s]
987.446237533 m 310.840393066 m 649.143315299 m
Image shape: (720, 1280, 3)
 92%|█████████▏| 1165/1261 [06:34<00:31,  3.00it/s]
1007.73609932 m 325.827434248 m 666.781766786 m
Image shape: (720, 1280, 3)
 92%|█████████▏| 1166/1261 [06:34<00:31,  2.99it/s]
934.15515906 m 389.61372758 m 661.88444332 m
Image shape: (720, 1280, 3)
 93%|█████████▎| 1167/1261 [06:34<00:31,  2.98it/s]
1111.63634565 m 339.731915998 m 725.684130824 m
Image shape: (720, 1280, 3)
 93%|█████████▎| 1168/1261 [06:35<00:31,  2.99it/s]
1031.01259779 m 295.283541846 m 663.148069816 m
Image shape: (720, 1280, 3)
 93%|█████████▎| 1169/1261 [06:35<00:30,  3.01it/s]
955.564931441 m 560.57698485 m 758.070958146 m
Image shape: (720, 1280, 3)
 93%|█████████▎| 1170/1261 [06:35<00:30,  3.02it/s]
908.836561455 m 759.618208175 m 834.227384815 m
Image shape: (720, 1280, 3)
 93%|█████████▎| 1171/1261 [06:36<00:29,  3.02it/s]
1019.88611158 m 591.242992188 m 805.564551883 m
Image shape: (720, 1280, 3)
 93%|█████████▎| 1172/1261 [06:36<00:29,  3.02it/s]
797.173608501 m 689.791403349 m 743.482505925 m
Image shape: (720, 1280, 3)
 93%|█████████▎| 1173/1261 [06:36<00:29,  3.00it/s]
873.206788933 m 381.05373391 m 627.130261421 m
Image shape: (720, 1280, 3)
 93%|█████████▎| 1174/1261 [06:37<00:28,  3.00it/s]
885.81246646 m 313.535580462 m 599.674023461 m
Image shape: (720, 1280, 3)
 93%|█████████▎| 1175/1261 [06:37<00:28,  3.00it/s]
917.960476848 m 302.662961244 m 610.311719046 m
Image shape: (720, 1280, 3)
 93%|█████████▎| 1176/1261 [06:37<00:28,  3.01it/s]
972.349272827 m 314.100204253 m 643.22473854 m
Image shape: (720, 1280, 3)
 93%|█████████▎| 1177/1261 [06:38<00:27,  3.01it/s]
1092.41881696 m 336.317974155 m 714.368395556 m
Image shape: (720, 1280, 3)
 93%|█████████▎| 1178/1261 [06:38<00:27,  3.00it/s]
1314.65918788 m 374.724114967 m 844.691651425 m
Image shape: (720, 1280, 3)
 93%|█████████▎| 1179/1261 [06:38<00:27,  3.00it/s]
1335.65566376 m 310.543448836 m 823.099556299 m
Image shape: (720, 1280, 3)
 94%|█████████▎| 1180/1261 [06:39<00:27,  2.99it/s]
1396.60814969 m 378.272594989 m 887.440372337 m
Image shape: (720, 1280, 3)
 94%|█████████▎| 1181/1261 [06:39<00:26,  3.00it/s]
2045.77857756 m 514.987170828 m 1280.3828742 m
Image shape: (720, 1280, 3)
 94%|█████████▎| 1182/1261 [06:39<00:26,  3.01it/s]
1167.20173298 m 602.074609388 m 884.638171185 m
Image shape: (720, 1280, 3)
 94%|█████████▍| 1183/1261 [06:40<00:25,  3.01it/s]
1173.68040028 m 554.953183456 m 864.316791869 m
Image shape: (720, 1280, 3)
 94%|█████████▍| 1184/1261 [06:40<00:25,  3.02it/s]
1040.04841054 m 367.664364979 m 703.856387761 m
Image shape: (720, 1280, 3)
 94%|█████████▍| 1185/1261 [06:40<00:25,  3.03it/s]
851.42585833 m 338.610360866 m 595.018109598 m
Image shape: (720, 1280, 3)
 94%|█████████▍| 1186/1261 [06:41<00:24,  3.02it/s]
937.68321906 m 290.495580512 m 614.089399786 m
Image shape: (720, 1280, 3)
 94%|█████████▍| 1187/1261 [06:41<00:24,  3.02it/s]
788.943466324 m 276.280015084 m 532.611740704 m
Image shape: (720, 1280, 3)
 94%|█████████▍| 1188/1261 [06:41<00:24,  3.03it/s]
740.065831863 m 276.618669441 m 508.342250652 m
Image shape: (720, 1280, 3)
 94%|█████████▍| 1189/1261 [06:42<00:23,  3.02it/s]
730.869692933 m 374.684472689 m 552.777082811 m
Image shape: (720, 1280, 3)
 94%|█████████▍| 1190/1261 [06:42<00:23,  3.01it/s]
745.117805632 m 251.937981634 m 498.527893633 m
Image shape: (720, 1280, 3)
 94%|█████████▍| 1191/1261 [06:42<00:23,  3.02it/s]
738.024038783 m 336.928617371 m 537.476328077 m
Image shape: (720, 1280, 3)
 95%|█████████▍| 1192/1261 [06:43<00:22,  3.03it/s]
730.101119906 m 522.38372517 m 626.242422538 m
Image shape: (720, 1280, 3)
 95%|█████████▍| 1193/1261 [06:43<00:22,  3.03it/s]
793.99624199 m 600.141143258 m 697.068692624 m
Image shape: (720, 1280, 3)
 95%|█████████▍| 1194/1261 [06:43<00:22,  3.03it/s]
641.486389932 m 463.946238291 m 552.716314112 m
Image shape: (720, 1280, 3)
 95%|█████████▍| 1195/1261 [06:44<00:21,  3.01it/s]
661.754923427 m 412.37636089 m 537.065642159 m
Image shape: (720, 1280, 3)
 95%|█████████▍| 1196/1261 [06:44<00:21,  3.02it/s]
666.560790563 m 384.132027891 m 525.346409227 m
Image shape: (720, 1280, 3)
 95%|█████████▍| 1197/1261 [06:44<00:21,  3.03it/s]
680.074351387 m 291.918722799 m 485.996537093 m
Image shape: (720, 1280, 3)
 95%|█████████▌| 1198/1261 [06:45<00:20,  3.03it/s]
744.252064472 m 313.089244263 m 528.670654368 m
Image shape: (720, 1280, 3)
 95%|█████████▌| 1199/1261 [06:45<00:20,  3.01it/s]
820.071410587 m 326.893619839 m 573.482515213 m
Image shape: (720, 1280, 3)
 95%|█████████▌| 1200/1261 [06:45<00:20,  3.01it/s]
882.663380148 m 365.302341504 m 623.982860826 m
Image shape: (720, 1280, 3)
 95%|█████████▌| 1201/1261 [06:46<00:19,  3.02it/s]
1154.61306898 m 310.267298233 m 732.440183604 m
Image shape: (720, 1280, 3)
 95%|█████████▌| 1202/1261 [06:46<00:19,  3.01it/s]
1317.75855673 m 316.719567769 m 817.239062248 m
Image shape: (720, 1280, 3)
 95%|█████████▌| 1203/1261 [06:46<00:19,  3.01it/s]
1207.20845102 m 371.229546045 m 789.218998531 m
Image shape: (720, 1280, 3)
 95%|█████████▌| 1204/1261 [06:47<00:18,  3.02it/s]
772.539008332 m 359.189923036 m 565.864465684 m
Image shape: (720, 1280, 3)
 96%|█████████▌| 1205/1261 [06:47<00:18,  3.02it/s]
732.951630552 m 531.495671288 m 632.22365092 m
Image shape: (720, 1280, 3)
 96%|█████████▌| 1206/1261 [06:47<00:18,  3.01it/s]
655.672558209 m 435.057827796 m 545.365193002 m
Image shape: (720, 1280, 3)
 96%|█████████▌| 1207/1261 [06:48<00:17,  3.02it/s]
637.498805912 m 324.090734689 m 480.7947703 m
Image shape: (720, 1280, 3)
 96%|█████████▌| 1208/1261 [06:48<00:17,  3.01it/s]
740.997858152 m 241.78578146 m 491.391819806 m
Image shape: (720, 1280, 3)
 96%|█████████▌| 1209/1261 [06:48<00:17,  3.01it/s]
702.615184371 m 256.864168313 m 479.739676342 m
Image shape: (720, 1280, 3)
 96%|█████████▌| 1210/1261 [06:49<00:17,  2.93it/s]
780.795309458 m 250.413119854 m 515.604214656 m
Image shape: (720, 1280, 3)
 96%|█████████▌| 1211/1261 [06:49<00:17,  2.91it/s]
690.447480637 m 286.390438775 m 488.418959706 m
Image shape: (720, 1280, 3)
 96%|█████████▌| 1212/1261 [06:49<00:17,  2.87it/s]
878.825961958 m 245.123184259 m 561.974573109 m
Image shape: (720, 1280, 3)
 96%|█████████▌| 1213/1261 [06:50<00:16,  2.90it/s]
807.957621019 m 261.643964362 m 534.80079269 m
Image shape: (720, 1280, 3)
 96%|█████████▋| 1214/1261 [06:50<00:16,  2.93it/s]
853.96103742 m 266.543641922 m 560.252339671 m
Image shape: (720, 1280, 3)
 96%|█████████▋| 1215/1261 [06:50<00:15,  2.95it/s]
878.382389862 m 305.785664923 m 592.084027392 m
Image shape: (720, 1280, 3)
 96%|█████████▋| 1216/1261 [06:51<00:15,  2.98it/s]
793.881450115 m 349.950847028 m 571.916148571 m
Image shape: (720, 1280, 3)
 97%|█████████▋| 1217/1261 [06:51<00:14,  2.97it/s]
726.548777996 m 443.088582485 m 584.818680241 m
Image shape: (720, 1280, 3)
 97%|█████████▋| 1218/1261 [06:51<00:14,  2.97it/s]
782.476034011 m 335.399688824 m 558.937861417 m
Image shape: (720, 1280, 3)
 97%|█████████▋| 1219/1261 [06:52<00:14,  2.99it/s]
735.000075844 m 281.559676905 m 508.279876375 m
Image shape: (720, 1280, 3)
 97%|█████████▋| 1220/1261 [06:52<00:13,  2.99it/s]
702.557970172 m 270.775333432 m 486.666651802 m
Image shape: (720, 1280, 3)
 97%|█████████▋| 1221/1261 [06:52<00:13,  3.00it/s]
839.554701392 m 288.80000698 m 564.177354186 m
Image shape: (720, 1280, 3)
 97%|█████████▋| 1222/1261 [06:53<00:12,  3.01it/s]
958.679082078 m 313.512689111 m 636.095885594 m
Image shape: (720, 1280, 3)
 97%|█████████▋| 1223/1261 [06:53<00:12,  3.00it/s]
851.261734649 m 279.453378948 m 565.357556799 m
Image shape: (720, 1280, 3)
 97%|█████████▋| 1224/1261 [06:53<00:12,  2.93it/s]
824.419711154 m 297.323877506 m 560.87179433 m
Image shape: (720, 1280, 3)
 97%|█████████▋| 1225/1261 [06:54<00:12,  2.94it/s]
694.877701381 m 296.986754282 m 495.932227832 m
Image shape: (720, 1280, 3)
 97%|█████████▋| 1226/1261 [06:54<00:11,  2.96it/s]
835.28748533 m 398.816514968 m 617.052000149 m
Image shape: (720, 1280, 3)
 97%|█████████▋| 1227/1261 [06:54<00:11,  2.96it/s]
839.686031227 m 374.500921172 m 607.093476199 m
Image shape: (720, 1280, 3)
 97%|█████████▋| 1228/1261 [06:55<00:11,  2.98it/s]
946.708410065 m 358.692592592 m 652.700501329 m
Image shape: (720, 1280, 3)
 97%|█████████▋| 1229/1261 [06:55<00:10,  2.99it/s]
1163.32152498 m 219.27823253 m 691.299878755 m
Image shape: (720, 1280, 3)
 98%|█████████▊| 1230/1261 [06:55<00:10,  2.98it/s]
968.23715241 m 275.714376318 m 621.975764364 m
Image shape: (720, 1280, 3)
 98%|█████████▊| 1231/1261 [06:56<00:10,  2.98it/s]
706.851842638 m 270.247492856 m 488.549667747 m
Image shape: (720, 1280, 3)
 98%|█████████▊| 1232/1261 [06:56<00:09,  2.99it/s]
756.350744845 m 299.799567491 m 528.075156168 m
Image shape: (720, 1280, 3)
 98%|█████████▊| 1233/1261 [06:56<00:09,  2.98it/s]
942.881561062 m 301.052733964 m 621.967147513 m
Image shape: (720, 1280, 3)
 98%|█████████▊| 1234/1261 [06:57<00:08,  3.01it/s]
1079.91535752 m 346.594945531 m 713.255151528 m
Image shape: (720, 1280, 3)
 98%|█████████▊| 1235/1261 [06:57<00:08,  3.01it/s]
1549.00155389 m 294.042720891 m 921.522137391 m
Image shape: (720, 1280, 3)
 98%|█████████▊| 1236/1261 [06:57<00:08,  3.01it/s]
1356.18376467 m 328.737001692 m 842.460383183 m
Image shape: (720, 1280, 3)
 98%|█████████▊| 1237/1261 [06:58<00:07,  3.02it/s]
2901.30380333 m 410.420276292 m 1655.86203981 m
Image shape: (720, 1280, 3)
 98%|█████████▊| 1238/1261 [06:58<00:07,  3.02it/s]
2828.98421569 m 504.21490005 m 1666.59955787 m
Image shape: (720, 1280, 3)
 98%|█████████▊| 1239/1261 [06:58<00:07,  3.05it/s]
2174.64525258 m 696.342602143 m 1435.49392736 m
Image shape: (720, 1280, 3)
 98%|█████████▊| 1240/1261 [06:59<00:06,  3.04it/s]
1884.26347638 m 465.159685315 m 1174.71158085 m
Image shape: (720, 1280, 3)
 98%|█████████▊| 1241/1261 [06:59<00:06,  3.03it/s]
2575.55073898 m 415.258010061 m 1495.40437452 m
Image shape: (720, 1280, 3)
 98%|█████████▊| 1242/1261 [06:59<00:06,  2.91it/s]
1876.96100028 m 349.392655164 m 1113.17682772 m
Image shape: (720, 1280, 3)
 99%|█████████▊| 1243/1261 [07:00<00:06,  2.74it/s]
1769.57199027 m 365.40858541 m 1067.49028784 m
Image shape: (720, 1280, 3)
 99%|█████████▊| 1244/1261 [07:00<00:06,  2.82it/s]
1785.58230266 m 362.113597497 m 1073.84795008 m
Image shape: (720, 1280, 3)
 99%|█████████▊| 1245/1261 [07:00<00:05,  2.87it/s]
2649.48991635 m 393.479255436 m 1521.48458589 m
Image shape: (720, 1280, 3)
 99%|█████████▉| 1246/1261 [07:01<00:05,  2.89it/s]
2272.00473765 m 372.935753404 m 1322.47024553 m
Image shape: (720, 1280, 3)
 99%|█████████▉| 1247/1261 [07:01<00:04,  2.93it/s]
1934.33394254 m 511.661168837 m 1222.99755569 m
Image shape: (720, 1280, 3)
 99%|█████████▉| 1248/1261 [07:01<00:04,  2.94it/s]
2084.01056147 m 613.20555349 m 1348.60805748 m
Image shape: (720, 1280, 3)
 99%|█████████▉| 1249/1261 [07:02<00:04,  2.93it/s]
2176.5147013 m 911.196862415 m 1543.85578186 m
Image shape: (720, 1280, 3)
 99%|█████████▉| 1250/1261 [07:02<00:03,  2.96it/s]
2660.8377099 m 1073.88680313 m 1867.36225652 m
Image shape: (720, 1280, 3)
 99%|█████████▉| 1251/1261 [07:02<00:03,  2.96it/s]
2322.04781338 m 703.683730634 m 1512.86577201 m
Image shape: (720, 1280, 3)
 99%|█████████▉| 1252/1261 [07:03<00:03,  2.95it/s]
1854.79727841 m 760.143883344 m 1307.47058088 m
Image shape: (720, 1280, 3)
 99%|█████████▉| 1253/1261 [07:03<00:02,  2.97it/s]
1964.84865906 m 706.649442088 m 1335.74905058 m
Image shape: (720, 1280, 3)
 99%|█████████▉| 1254/1261 [07:03<00:02,  2.98it/s]
5357.67313972 m 816.801545262 m 3087.23734249 m
Image shape: (720, 1280, 3)
100%|█████████▉| 1255/1261 [07:04<00:02,  2.98it/s]
4287.65798038 m 1004.96946966 m 2646.31372502 m
Image shape: (720, 1280, 3)
100%|█████████▉| 1256/1261 [07:04<00:01,  2.98it/s]
25403.002844 m 522.096288619 m 12962.5495663 m
Image shape: (720, 1280, 3)
100%|█████████▉| 1257/1261 [07:04<00:01,  2.97it/s]
16122.805653 m 492.410771582 m 8307.60821229 m
Image shape: (720, 1280, 3)
100%|█████████▉| 1258/1261 [07:05<00:01,  2.98it/s]
16697.0926874 m 584.486281075 m 8640.78948424 m
Image shape: (720, 1280, 3)
100%|█████████▉| 1259/1261 [07:05<00:00,  2.98it/s]
3729.82341248 m 573.397930045 m 2151.61067126 m
Image shape: (720, 1280, 3)
100%|█████████▉| 1260/1261 [07:05<00:00,  3.00it/s]
3385.30260696 m 769.390289208 m 2077.34644809 m

[MoviePy] Done.
[MoviePy] >>>> Video ready: project_video_out5.mp4 

CPU times: user 7min 8s, sys: 1min 58s, total: 9min 7s
Wall time: 7min 6s
In [54]:
def printImage(img):
    global Count
    #plt.imshow(img)
    print (Count)
    filename = "test/" + str(Count) + '.jpg'
    print (filename)
    img2 = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
    cv2.imwrite(filename, img2)
    result = process_image2(img)
    filename = "test/" + str(Count) + 'processed.jpg'
    cv2.imwrite(filename, result)
    Count = Count + 1
    return result
In [55]:
subclip = VideoFileClip("project_video.mp4").subclip(41, 42)
video_out2 = "project_video_out_sub14142.mp4"
Count = 0
In [56]:
video_printed = subclip.fl_image(printImage)
video_printed.write_videofile("test.mp4", audio=False)
0
test/0.jpg
Image shape: (720, 1280, 3)
306.802388352 m 297.211035759 m 302.006712056 m
[MoviePy] >>>> Building video test.mp4
[MoviePy] Writing video test.mp4
  0%|          | 0/26 [00:00<?, ?it/s]
1
test/1.jpg
Image shape: (720, 1280, 3)
  4%|▍         | 1/26 [00:00<00:10,  2.30it/s]
306.802388352 m 297.211035759 m 302.006712056 m
2
test/2.jpg
Image shape: (720, 1280, 3)
  8%|▊         | 2/26 [00:00<00:10,  2.31it/s]
241.14544093 m 200.881361742 m 221.013401336 m
3
test/3.jpg
Image shape: (720, 1280, 3)
 12%|█▏        | 3/26 [00:01<00:09,  2.34it/s]
170.983220999 m 226.667276104 m 198.825248551 m
4
test/4.jpg
Image shape: (720, 1280, 3)
 15%|█▌        | 4/26 [00:01<00:09,  2.32it/s]
202.186389503 m 190.829169671 m 196.507779587 m
5
test/5.jpg
Image shape: (720, 1280, 3)
 19%|█▉        | 5/26 [00:02<00:08,  2.33it/s]
246.96980138 m 243.572308217 m 245.271054798 m
6
test/6.jpg
Image shape: (720, 1280, 3)
 23%|██▎       | 6/26 [00:02<00:08,  2.34it/s]
207.247106447 m 248.614767427 m 227.930936937 m
7
test/7.jpg
Image shape: (720, 1280, 3)
 27%|██▋       | 7/26 [00:02<00:08,  2.35it/s]
261.661972302 m 278.173276902 m 269.917624602 m
8
test/8.jpg
Image shape: (720, 1280, 3)
 31%|███       | 8/26 [00:03<00:07,  2.37it/s]
424.006300569 m 393.998297806 m 409.002299188 m
9
test/9.jpg
Image shape: (720, 1280, 3)
 35%|███▍      | 9/26 [00:03<00:07,  2.39it/s]
621.729347666 m 809.724216326 m 715.726781996 m
10
test/10.jpg
Image shape: (720, 1280, 3)
 38%|███▊      | 10/26 [00:04<00:06,  2.40it/s]
692.437542315 m 430.569449553 m 561.503495934 m
11
test/11.jpg
Image shape: (720, 1280, 3)
 42%|████▏     | 11/26 [00:04<00:06,  2.41it/s]
700.802303199 m 266.136438999 m 483.469371099 m
12
test/12.jpg
Image shape: (720, 1280, 3)
 46%|████▌     | 12/26 [00:05<00:05,  2.43it/s]
821.985531608 m 276.535994181 m 549.260762894 m
13
test/13.jpg
Image shape: (720, 1280, 3)
 50%|█████     | 13/26 [00:05<00:05,  2.43it/s]
573.012956533 m 260.878576681 m 416.945766607 m
14
test/14.jpg
Image shape: (720, 1280, 3)
 54%|█████▍    | 14/26 [00:05<00:04,  2.44it/s]
479.886972699 m 293.682662835 m 386.784817767 m
15
test/15.jpg
Image shape: (720, 1280, 3)
 58%|█████▊    | 15/26 [00:06<00:04,  2.44it/s]
524.784702783 m 324.081170584 m 424.432936684 m
16
test/16.jpg
Image shape: (720, 1280, 3)
 62%|██████▏   | 16/26 [00:06<00:04,  2.45it/s]
567.120117654 m 194.368200135 m 380.744158895 m
17
test/17.jpg
Image shape: (720, 1280, 3)
 65%|██████▌   | 17/26 [00:07<00:03,  2.45it/s]
589.361115954 m 1060.26499289 m 824.813054423 m
18
test/18.jpg
Image shape: (720, 1280, 3)
 69%|██████▉   | 18/26 [00:07<00:03,  2.46it/s]
546.146962063 m 578.480662924 m 562.313812494 m
19
test/19.jpg
Image shape: (720, 1280, 3)
 73%|███████▎  | 19/26 [00:07<00:02,  2.46it/s]
398.715482499 m 689.168664123 m 543.942073311 m
20
test/20.jpg
Image shape: (720, 1280, 3)
 77%|███████▋  | 20/26 [00:08<00:02,  2.46it/s]
427.509870706 m 582.705108383 m 505.107489545 m
21
test/21.jpg
Image shape: (720, 1280, 3)
 81%|████████  | 21/26 [00:08<00:02,  2.46it/s]
312.033804309 m 547.476320448 m 429.755062379 m
22
test/22.jpg
Image shape: (720, 1280, 3)
 85%|████████▍ | 22/26 [00:09<00:01,  2.47it/s]
350.425004142 m 302.602472756 m 326.513738449 m
23
test/23.jpg
Image shape: (720, 1280, 3)
 88%|████████▊ | 23/26 [00:09<00:01,  2.46it/s]
478.734531415 m 295.042644883 m 386.888588149 m
24
test/24.jpg
Image shape: (720, 1280, 3)
 92%|█████████▏| 24/26 [00:09<00:00,  2.45it/s]
477.524826663 m 235.585791927 m 356.555309295 m
25
test/25.jpg
Image shape: (720, 1280, 3)
 96%|█████████▌| 25/26 [00:10<00:00,  2.45it/s]
532.817047976 m 272.35667538 m 402.586861678 m

[MoviePy] Done.
[MoviePy] >>>> Video ready: test.mp4 

In [57]:
video_cap2 = subclip.fl_image(process_image2)
%time video_cap2.write_videofile(video_out2, audio=False)
Image shape: (720, 1280, 3)
306.802388352 m 297.211035759 m 302.006712056 m
[MoviePy] >>>> Building video project_video_out_sub14142.mp4
[MoviePy] Writing video project_video_out_sub14142.mp4
  0%|          | 0/26 [00:00<?, ?it/s]
Image shape: (720, 1280, 3)
  4%|▍         | 1/26 [00:00<00:08,  2.87it/s]
306.802388352 m 297.211035759 m 302.006712056 m
Image shape: (720, 1280, 3)
  8%|▊         | 2/26 [00:00<00:08,  2.87it/s]
241.14544093 m 200.881361742 m 221.013401336 m
Image shape: (720, 1280, 3)
 12%|█▏        | 3/26 [00:01<00:08,  2.87it/s]
170.983220999 m 226.667276104 m 198.825248551 m
Image shape: (720, 1280, 3)
 15%|█▌        | 4/26 [00:01<00:07,  2.83it/s]
202.186389503 m 190.829169671 m 196.507779587 m
Image shape: (720, 1280, 3)
 19%|█▉        | 5/26 [00:01<00:07,  2.82it/s]
246.96980138 m 243.572308217 m 245.271054798 m
Image shape: (720, 1280, 3)
 23%|██▎       | 6/26 [00:02<00:07,  2.83it/s]
207.247106447 m 248.614767427 m 227.930936937 m
Image shape: (720, 1280, 3)
 27%|██▋       | 7/26 [00:02<00:06,  2.85it/s]
261.661972302 m 278.173276902 m 269.917624602 m
Image shape: (720, 1280, 3)
 31%|███       | 8/26 [00:02<00:06,  2.88it/s]
424.006300569 m 393.998297806 m 409.002299188 m
Image shape: (720, 1280, 3)
 35%|███▍      | 9/26 [00:03<00:05,  2.91it/s]
621.729347666 m 809.724216326 m 715.726781996 m
Image shape: (720, 1280, 3)
 38%|███▊      | 10/26 [00:03<00:05,  2.92it/s]
692.437542315 m 430.569449553 m 561.503495934 m
Image shape: (720, 1280, 3)
 42%|████▏     | 11/26 [00:03<00:05,  2.93it/s]
700.802303199 m 266.136438999 m 483.469371099 m
Image shape: (720, 1280, 3)
 46%|████▌     | 12/26 [00:04<00:04,  2.95it/s]
821.985531608 m 276.535994181 m 549.260762894 m
Image shape: (720, 1280, 3)
 50%|█████     | 13/26 [00:04<00:04,  2.94it/s]
573.012956533 m 260.878576681 m 416.945766607 m
Image shape: (720, 1280, 3)
 54%|█████▍    | 14/26 [00:04<00:04,  2.90it/s]
479.886972699 m 293.682662835 m 386.784817767 m
Image shape: (720, 1280, 3)
 58%|█████▊    | 15/26 [00:05<00:03,  2.89it/s]
524.784702783 m 324.081170584 m 424.432936684 m
Image shape: (720, 1280, 3)
 62%|██████▏   | 16/26 [00:05<00:03,  2.89it/s]
567.120117654 m 194.368200135 m 380.744158895 m
Image shape: (720, 1280, 3)
 65%|██████▌   | 17/26 [00:05<00:03,  2.90it/s]
589.361115954 m 1060.26499289 m 824.813054423 m
Image shape: (720, 1280, 3)
 69%|██████▉   | 18/26 [00:06<00:02,  2.91it/s]
546.146962063 m 578.480662924 m 562.313812494 m
Image shape: (720, 1280, 3)
 73%|███████▎  | 19/26 [00:06<00:02,  2.93it/s]
398.715482499 m 689.168664123 m 543.942073311 m
Image shape: (720, 1280, 3)
 77%|███████▋  | 20/26 [00:06<00:02,  2.95it/s]
427.509870706 m 582.705108383 m 505.107489545 m
Image shape: (720, 1280, 3)
 81%|████████  | 21/26 [00:07<00:01,  2.96it/s]
312.033804309 m 547.476320448 m 429.755062379 m
Image shape: (720, 1280, 3)
 85%|████████▍ | 22/26 [00:07<00:01,  2.97it/s]
350.425004142 m 302.602472756 m 326.513738449 m
Image shape: (720, 1280, 3)
 88%|████████▊ | 23/26 [00:07<00:01,  2.97it/s]
478.734531415 m 295.042644883 m 386.888588149 m
Image shape: (720, 1280, 3)
 92%|█████████▏| 24/26 [00:08<00:00,  2.97it/s]
477.524826663 m 235.585791927 m 356.555309295 m
Image shape: (720, 1280, 3)
 96%|█████████▌| 25/26 [00:08<00:00,  2.95it/s]
532.817047976 m 272.35667538 m 402.586861678 m

[MoviePy] Done.
[MoviePy] >>>> Video ready: project_video_out_sub14142.mp4 

CPU times: user 8.65 s, sys: 2.48 s, total: 11.1 s
Wall time: 9.27 s
In [58]:
subclip = VideoFileClip("project_video.mp4").subclip(23, 24)
video_out2 = "project_video_out_sub2324.mp4"
Count = 0
In [59]:
video_cap2 = subclip.fl_image(process_image2)
%time video_cap2.write_videofile(video_out2, audio=False)
Image shape: (720, 1280, 3)
14042.3041432 m 2370.10590927 m 8206.20502623 m
[MoviePy] >>>> Building video project_video_out_sub2324.mp4
[MoviePy] Writing video project_video_out_sub2324.mp4
  0%|          | 0/26 [00:00<?, ?it/s]
Image shape: (720, 1280, 3)
  4%|▍         | 1/26 [00:00<00:09,  2.78it/s]
14042.3041432 m 2370.10590927 m 8206.20502623 m
Image shape: (720, 1280, 3)
  8%|▊         | 2/26 [00:00<00:08,  2.79it/s]
8629.3641652 m 671.203660553 m 4650.28391288 m
Image shape: (720, 1280, 3)
 12%|█▏        | 3/26 [00:01<00:08,  2.81it/s]
8688.06778402 m 554.162102236 m 4621.11494313 m
Image shape: (720, 1280, 3)
 15%|█▌        | 4/26 [00:01<00:07,  2.84it/s]
17203.5124233 m 1307.60276627 m 9255.55759477 m
Image shape: (720, 1280, 3)
 19%|█▉        | 5/26 [00:01<00:07,  2.85it/s]
8693.7380412 m 1089.65578694 m 4891.69691407 m
Image shape: (720, 1280, 3)
 23%|██▎       | 6/26 [00:02<00:07,  2.85it/s]
6222.5417893 m 519.808939806 m 3371.17536455 m
Image shape: (720, 1280, 3)
 27%|██▋       | 7/26 [00:02<00:06,  2.84it/s]
5646.71271279 m 368.564787206 m 3007.63875 m
Image shape: (720, 1280, 3)
 31%|███       | 8/26 [00:02<00:06,  2.85it/s]
5045.33756505 m 509.00275113 m 2777.17015809 m
Image shape: (720, 1280, 3)
 35%|███▍      | 9/26 [00:03<00:05,  2.86it/s]
2488.82188262 m 471.762813167 m 1480.2923479 m
Image shape: (720, 1280, 3)
 38%|███▊      | 10/26 [00:03<00:05,  2.89it/s]
2038.11756578 m 877.202035022 m 1457.6598004 m
Image shape: (720, 1280, 3)
 42%|████▏     | 11/26 [00:03<00:05,  2.86it/s]
2620.39960357 m 1429.61076001 m 2025.00518179 m
Image shape: (720, 1280, 3)
 46%|████▌     | 12/26 [00:04<00:04,  2.88it/s]
2589.58483747 m 26479.8938507 m 14534.7393441 m
Image shape: (720, 1280, 3)
 50%|█████     | 13/26 [00:04<00:04,  2.90it/s]
2519.23954123 m 5606.16229147 m 4062.70091635 m
Image shape: (720, 1280, 3)
 54%|█████▍    | 14/26 [00:04<00:04,  2.90it/s]
9422.68820851 m 390.68304202 m 4906.68562526 m
Image shape: (720, 1280, 3)
 58%|█████▊    | 15/26 [00:05<00:03,  2.90it/s]
1825.80010754 m 401.927605576 m 1113.86385656 m
Image shape: (720, 1280, 3)
 62%|██████▏   | 16/26 [00:05<00:03,  2.89it/s]
3033.20676618 m 435.347065343 m 1734.27691576 m
Image shape: (720, 1280, 3)
 65%|██████▌   | 17/26 [00:05<00:03,  2.88it/s]
4305.83741922 m 532.413326837 m 2419.12537303 m
Image shape: (720, 1280, 3)
 69%|██████▉   | 18/26 [00:06<00:02,  2.87it/s]
75493.4034075 m 455.996709124 m 37974.7000583 m
Image shape: (720, 1280, 3)
 73%|███████▎  | 19/26 [00:06<00:02,  2.87it/s]
4063.00208238 m 314.30175778 m 2188.65192008 m
Image shape: (720, 1280, 3)
 77%|███████▋  | 20/26 [00:06<00:02,  2.88it/s]
3923.26618058 m 478.679226504 m 2200.97270354 m
Image shape: (720, 1280, 3)
 81%|████████  | 21/26 [00:07<00:01,  2.88it/s]
8267.50964179 m 534.118500703 m 4400.81407125 m
Image shape: (720, 1280, 3)
 85%|████████▍ | 22/26 [00:07<00:01,  2.88it/s]
79402.593793 m 651.14471919 m 40026.8692561 m
Image shape: (720, 1280, 3)
 88%|████████▊ | 23/26 [00:08<00:01,  2.89it/s]
27445.2054575 m 374.115198253 m 13909.6603279 m
Image shape: (720, 1280, 3)
 92%|█████████▏| 24/26 [00:08<00:00,  2.89it/s]
11546.7566409 m 199.469710077 m 5873.11317548 m
Image shape: (720, 1280, 3)
 96%|█████████▌| 25/26 [00:08<00:00,  2.89it/s]
24554.1742347 m 136.434227766 m 12345.3042313 m

[MoviePy] Done.
[MoviePy] >>>> Video ready: project_video_out_sub2324.mp4 

CPU times: user 8.75 s, sys: 2.53 s, total: 11.3 s
Wall time: 9.27 s
In [ ]:
 
In [60]:
video_printed = subclip.fl_image(printImage)
video_printed.write_videofile("test.mp4", audio=False)
0
test/0.jpg
Image shape: (720, 1280, 3)
14042.3041432 m 2370.10590927 m 8206.20502623 m
[MoviePy] >>>> Building video test.mp4
[MoviePy] Writing video test.mp4
  0%|          | 0/26 [00:00<?, ?it/s]
1
test/1.jpg
Image shape: (720, 1280, 3)
  4%|▍         | 1/26 [00:00<00:11,  2.26it/s]
14042.3041432 m 2370.10590927 m 8206.20502623 m
2
test/2.jpg
Image shape: (720, 1280, 3)
  8%|▊         | 2/26 [00:00<00:10,  2.29it/s]
8629.3641652 m 671.203660553 m 4650.28391288 m
3
test/3.jpg
Image shape: (720, 1280, 3)
 12%|█▏        | 3/26 [00:01<00:09,  2.33it/s]
8688.06778402 m 554.162102236 m 4621.11494313 m
4
test/4.jpg
Image shape: (720, 1280, 3)
 15%|█▌        | 4/26 [00:01<00:09,  2.36it/s]
17203.5124233 m 1307.60276627 m 9255.55759477 m
5
test/5.jpg
Image shape: (720, 1280, 3)
 19%|█▉        | 5/26 [00:02<00:08,  2.36it/s]
8693.7380412 m 1089.65578694 m 4891.69691407 m
6
test/6.jpg
Image shape: (720, 1280, 3)
 23%|██▎       | 6/26 [00:02<00:08,  2.37it/s]
6222.5417893 m 519.808939806 m 3371.17536455 m
7
test/7.jpg
Image shape: (720, 1280, 3)
 27%|██▋       | 7/26 [00:02<00:08,  2.37it/s]
5646.71271279 m 368.564787206 m 3007.63875 m
8
test/8.jpg
Image shape: (720, 1280, 3)
 31%|███       | 8/26 [00:03<00:07,  2.40it/s]
5045.33756505 m 509.00275113 m 2777.17015809 m
9
test/9.jpg
Image shape: (720, 1280, 3)
 35%|███▍      | 9/26 [00:03<00:07,  2.39it/s]
2488.82188262 m 471.762813167 m 1480.2923479 m
10
test/10.jpg
Image shape: (720, 1280, 3)
 38%|███▊      | 10/26 [00:04<00:06,  2.36it/s]
2038.11756578 m 877.202035022 m 1457.6598004 m
11
test/11.jpg
Image shape: (720, 1280, 3)
 42%|████▏     | 11/26 [00:04<00:06,  2.32it/s]
2620.39960357 m 1429.61076001 m 2025.00518179 m
12
test/12.jpg
Image shape: (720, 1280, 3)
 46%|████▌     | 12/26 [00:05<00:05,  2.37it/s]
2589.58483747 m 26479.8938507 m 14534.7393441 m
13
test/13.jpg
Image shape: (720, 1280, 3)
 50%|█████     | 13/26 [00:05<00:05,  2.40it/s]
2519.23954123 m 5606.16229147 m 4062.70091635 m
14
test/14.jpg
Image shape: (720, 1280, 3)
 54%|█████▍    | 14/26 [00:05<00:04,  2.41it/s]
9422.68820851 m 390.68304202 m 4906.68562526 m
15
test/15.jpg
Image shape: (720, 1280, 3)
 58%|█████▊    | 15/26 [00:06<00:04,  2.42it/s]
1825.80010754 m 401.927605576 m 1113.86385656 m
16
test/16.jpg
Image shape: (720, 1280, 3)
 62%|██████▏   | 16/26 [00:06<00:04,  2.37it/s]
3033.20676618 m 435.347065343 m 1734.27691576 m
17
test/17.jpg
Image shape: (720, 1280, 3)
 65%|██████▌   | 17/26 [00:07<00:03,  2.38it/s]
4305.83741922 m 532.413326837 m 2419.12537303 m
18
test/18.jpg
Image shape: (720, 1280, 3)
 69%|██████▉   | 18/26 [00:07<00:03,  2.41it/s]
75493.4034075 m 455.996709124 m 37974.7000583 m
19
test/19.jpg
Image shape: (720, 1280, 3)
 73%|███████▎  | 19/26 [00:07<00:02,  2.39it/s]
4063.00208238 m 314.30175778 m 2188.65192008 m
20
test/20.jpg
Image shape: (720, 1280, 3)
 77%|███████▋  | 20/26 [00:08<00:02,  2.39it/s]
3923.26618058 m 478.679226504 m 2200.97270354 m
21
test/21.jpg
Image shape: (720, 1280, 3)
 81%|████████  | 21/26 [00:08<00:02,  2.42it/s]
8267.50964179 m 534.118500703 m 4400.81407125 m
22
test/22.jpg
Image shape: (720, 1280, 3)
 85%|████████▍ | 22/26 [00:09<00:01,  2.41it/s]
79402.593793 m 651.14471919 m 40026.8692561 m
23
test/23.jpg
Image shape: (720, 1280, 3)
 88%|████████▊ | 23/26 [00:09<00:01,  2.42it/s]
27445.2054575 m 374.115198253 m 13909.6603279 m
24
test/24.jpg
Image shape: (720, 1280, 3)
 92%|█████████▏| 24/26 [00:10<00:00,  2.40it/s]
11546.7566409 m 199.469710077 m 5873.11317548 m
25
test/25.jpg
Image shape: (720, 1280, 3)
 96%|█████████▌| 25/26 [00:10<00:00,  2.42it/s]
24554.1742347 m 136.434227766 m 12345.3042313 m

[MoviePy] Done.
[MoviePy] >>>> Video ready: test.mp4 

In [ ]: